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

Dataset: Open Web Text

Neuron 3071 in Layer 2

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: 5.0153. Min Range: -5.0153

Max Act: 5.0153. Min Act: -0.1700

Data Index: 2409136 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.9356. Min Act: -0.1700

Data Index: 6354710 (Open Web Text)

Max Activating Token Index: 456

Text #2

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.9178. Min Act: -0.1700

Data Index: 2057067 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8943. Min Act: -0.1700

Data Index: 4534842 (Open Web Text)

Max Activating Token Index: 938

Text #4

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8751. Min Act: -0.1700

Data Index: 6088664 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.9131. Min Act: -0.1700

Data Index: 1811032 (Open Web Text)

Max Activating Token Index: 735

Text #6

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8854. Min Act: -0.1700

Data Index: 5387525 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8882. Min Act: -0.1700

Data Index: 8528537 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8456. Min Act: -0.1700

Data Index: 3498372 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8535. Min Act: -0.1700

Data Index: 420262 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8393. Min Act: -0.1700

Data Index: 5291552 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8428. Min Act: -0.1700

Data Index: 3844632 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.7962. Min Act: -0.1700

Data Index: 6138966 (Open Web Text)

Max Activating Token Index: 835

Text #13

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8119. Min Act: -0.1700

Data Index: 6306894 (Open Web Text)

Max Activating Token Index: 563

Text #14

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8343. Min Act: -0.1700

Data Index: 5207721 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8109. Min Act: -0.1700

Data Index: 439761 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8109. Min Act: -0.1700

Data Index: 7221859 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8257. Min Act: -0.1700

Data Index: 8024934 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8267. Min Act: -0.1700

Data Index: 1567847 (Open Web Text)

Max Activating Token Index: 122

Text #19

Max Range: 5.0153. Min Range: -5.0153

Max Act: 4.8203. Min Act: -0.1700

Data Index: 5371582 (Open Web Text)

Max Activating Token Index: 119