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

Dataset: Open Web Text

Neuron 93 in Layer 3

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: 3.9039. Min Range: -3.9039

Max Act: 3.9039. Min Act: -0.1700

Data Index: 1501059 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8721. Min Act: -0.1700

Data Index: 311580 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 2491337 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 4061046 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 3969251 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 897558 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 3897205 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 391546 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 1254004 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 4602494 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 3039674 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 4517324 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 1424604 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 2429367 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 746381 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 2413007 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 4300370 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 2120912 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 1655586 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.9039. Min Range: -3.9039

Max Act: 3.8562. Min Act: -0.1700

Data Index: 1442693 (Open Web Text)

Max Activating Token Index: 2