< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2001 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.2013. Min Act: -0.1023

Data Index: 1613044 (Open Web Text)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.1144. Min Act: -0.0259

Data Index: 4370044 (Open Web Text)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.1121. Min Act: -0.1113

Data Index: 4681729 (Open Web Text)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.1080. Min Act: -0.0262

Data Index: 5798086 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.1066. Min Act: -0.0366

Data Index: 1224860 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.1091. Min Act: -0.1167

Data Index: 6177017 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.1012. Min Act: -0.1191

Data Index: 8160740 (Open Web Text)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0951. Min Act: -0.1135

Data Index: 7705135 (Open Web Text)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0958. Min Act: -0.0974

Data Index: 3461080 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0882. Min Act: -0.0978

Data Index: 6203061 (Open Web Text)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0902. Min Act: -0.1010

Data Index: 1691310 (Open Web Text)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0799. Min Act: -0.1093

Data Index: 905451 (Open Web Text)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0735. Min Act: -0.0972

Data Index: 300919 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0712. Min Act: -0.0104

Data Index: 7421037 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0650. Min Act: -0.1128

Data Index: 439149 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0728. Min Act: -0.0975

Data Index: 6485821 (Open Web Text)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0708. Min Act: -0.0954

Data Index: 7288216 (Open Web Text)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0672. Min Act: -0.1103

Data Index: 6843690 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0680. Min Act: -0.0798

Data Index: 7452835 (Open Web Text)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 1.2013. Min Range: -1.2013

Max Act: 1.0741. Min Act: -0.1319

Data Index: 6751169 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #19