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

Dataset: Open Web Text

Neuron 2814 in Layer 1

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: 0.3022. Min Range: -0.3022

Max Act: 0.3022. Min Act: -0.1671

Data Index: 4514350 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2740. Min Act: -0.1626

Data Index: 3952494 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2809. Min Act: -0.1698

Data Index: 1255664 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2582. Min Act: -0.1698

Data Index: 1522736 (Open Web Text)

Max Activating Token Index: 967

Text #4

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2570. Min Act: -0.1696

Data Index: 7043599 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2570. Min Act: -0.1689

Data Index: 503029 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2410. Min Act: -0.1696

Data Index: 1830627 (Open Web Text)

Max Activating Token Index: 285

Text #7

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2495. Min Act: -0.1700

Data Index: 8649461 (Open Web Text)

Max Activating Token Index: 996

Text #8

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2400. Min Act: -0.1674

Data Index: 6517687 (Open Web Text)

Max Activating Token Index: 100

Text #9

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2371. Min Act: -0.1630

Data Index: 6517688 (Open Web Text)

Max Activating Token Index: 102

Text #10

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2252. Min Act: -0.1696

Data Index: 8595608 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2196. Min Act: -0.1698

Data Index: 5285440 (Open Web Text)

Max Activating Token Index: 559

Text #12

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2220. Min Act: -0.1698

Data Index: 8792514 (Open Web Text)

Max Activating Token Index: 272

Text #13

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2208. Min Act: -0.1700

Data Index: 7856231 (Open Web Text)

Max Activating Token Index: 509

Text #14

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2157. Min Act: -0.1695

Data Index: 6299088 (Open Web Text)

Max Activating Token Index: 223

Text #15

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2168. Min Act: -0.1690

Data Index: 3561443 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2104. Min Act: -0.1699

Data Index: 6430896 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2042. Min Act: -0.1700

Data Index: 5283627 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2101. Min Act: -0.1699

Data Index: 5735340 (Open Web Text)

Max Activating Token Index: 175

Text #19

Max Range: 0.3022. Min Range: -0.3022

Max Act: 0.2061. Min Act: -0.1612

Data Index: 4893971 (Open Web Text)

Max Activating Token Index: 966