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

Dataset: Open Web Text

Neuron 2643 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: 5.1058. Min Range: -5.1058

Max Act: 5.1058. Min Act: -0.1700

Data Index: 4261739 (Open Web Text)

Max Activating Token Index: 118

Text #1

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0995. Min Act: -0.1700

Data Index: 4857786 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0989. Min Act: -0.1700

Data Index: 1757723 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0568. Min Act: -0.1700

Data Index: 2183911 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0611. Min Act: -0.1700

Data Index: 5793111 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0576. Min Act: -0.1700

Data Index: 407126 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0576. Min Act: -0.1700

Data Index: 6639185 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0576. Min Act: -0.1700

Data Index: 1797806 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0190. Min Act: -0.1700

Data Index: 7440844 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0075. Min Act: -0.1700

Data Index: 2089693 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0190. Min Act: -0.1700

Data Index: 1021972 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9964. Min Act: -0.1700

Data Index: 4017129 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9828. Min Act: -0.1700

Data Index: 7300120 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0055. Min Act: -0.1700

Data Index: 3105059 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 5.1058. Min Range: -5.1058

Max Act: 5.0048. Min Act: -0.1700

Data Index: 3251527 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9593. Min Act: -0.1700

Data Index: 2796146 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9448. Min Act: -0.1700

Data Index: 3721574 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9635. Min Act: -0.1700

Data Index: 742390 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9534. Min Act: -0.1700

Data Index: 256821 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 5.1058. Min Range: -5.1058

Max Act: 4.9657. Min Act: -0.1700

Data Index: 3152093 (Open Web Text)

Max Activating Token Index: 4