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

Dataset: Open Web Text

Neuron 2008 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: 2.8918. Min Range: -2.8918

Max Act: 2.8918. Min Act: -0.1700

Data Index: 7347541 (Open Web Text)

Max Activating Token Index: 736

Text #1

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8744. Min Act: -0.1700

Data Index: 4890528 (Open Web Text)

Max Activating Token Index: 712

Text #2

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8776. Min Act: -0.1700

Data Index: 554574 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8072. Min Act: -0.1700

Data Index: 1478591 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7912. Min Act: -0.1700

Data Index: 4598954 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7883. Min Act: -0.1700

Data Index: 8312857 (Open Web Text)

Max Activating Token Index: 170

Text #6

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7668. Min Act: -0.1700

Data Index: 3485427 (Open Web Text)

Max Activating Token Index: 945

Text #7

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7590. Min Act: -0.1700

Data Index: 1285438 (Open Web Text)

Max Activating Token Index: 556

Text #8

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7850. Min Act: -0.1700

Data Index: 3111733 (Open Web Text)

Max Activating Token Index: 822

Text #9

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7777. Min Act: -0.1700

Data Index: 3429850 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7320. Min Act: -0.1700

Data Index: 4814317 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7308. Min Act: -0.1700

Data Index: 5216427 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7419. Min Act: -0.1700

Data Index: 5718226 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7152. Min Act: -0.1700

Data Index: 3536198 (Open Web Text)

Max Activating Token Index: 985

Text #14

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7214. Min Act: -0.1700

Data Index: 8379444 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7005. Min Act: -0.1700

Data Index: 7128457 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7279. Min Act: -0.1700

Data Index: 5160653 (Open Web Text)

Max Activating Token Index: 51

Text #17

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7121. Min Act: -0.1700

Data Index: 2840013 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.6932. Min Act: -0.1700

Data Index: 5867206 (Open Web Text)

Max Activating Token Index: 806

Text #19

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7223. Min Act: -0.1700

Data Index: 629636 (Open Web Text)

Max Activating Token Index: 5