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

Dataset: Open Web Text

Neuron 462 in Layer 4

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: 2.2647. Min Range: -2.2647

Max Act: 2.2647. Min Act: -0.1644

Data Index: 6599730 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2567. Min Act: -0.1697

Data Index: 6475661 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2406. Min Act: -0.1700

Data Index: 6700407 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2336. Min Act: -0.1693

Data Index: 170076 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2315. Min Act: -0.1700

Data Index: 2672890 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2186. Min Act: -0.1700

Data Index: 2861111 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2065. Min Act: -0.1685

Data Index: 4991331 (Open Web Text)

Max Activating Token Index: 581

Text #7

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2130. Min Act: -0.1700

Data Index: 8696277 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2057. Min Act: -0.1700

Data Index: 1043696 (Open Web Text)

Max Activating Token Index: 134

Text #9

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2022. Min Act: -0.1684

Data Index: 8641527 (Open Web Text)

Max Activating Token Index: 165

Text #10

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2158. Min Act: -0.1698

Data Index: 8188980 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1922. Min Act: -0.1699

Data Index: 4103654 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1840. Min Act: -0.1700

Data Index: 494380 (Open Web Text)

Max Activating Token Index: 356

Text #13

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1982. Min Act: -0.1673

Data Index: 1271502 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1877. Min Act: -0.1692

Data Index: 7947986 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1980. Min Act: -0.1694

Data Index: 6338307 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1933. Min Act: -0.1700

Data Index: 7573319 (Open Web Text)

Max Activating Token Index: 232

Text #17

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1823. Min Act: -0.1693

Data Index: 6785457 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.2055. Min Act: -0.1699

Data Index: 5830308 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 2.2647. Min Range: -2.2647

Max Act: 2.1781. Min Act: -0.1700

Data Index: 1192914 (Open Web Text)

Max Activating Token Index: 273