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

Dataset: Open Web Text

Neuron 988 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: 4.6071. Min Range: -4.6071

Max Act: 4.6071. Min Act: -0.1700

Data Index: 2080200 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.5321. Min Act: -0.1700

Data Index: 1836069 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.4821. Min Act: -0.1700

Data Index: 1184917 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.5055. Min Act: -0.1700

Data Index: 1962880 (Open Web Text)

Max Activating Token Index: 170

Text #4

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.4973. Min Act: -0.1700

Data Index: 3718027 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.5057. Min Act: -0.1700

Data Index: 219933 (Open Web Text)

Max Activating Token Index: 587

Text #6

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.4372. Min Act: -0.1700

Data Index: 6678816 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.4121. Min Act: -0.1700

Data Index: 1382114 (Open Web Text)

Max Activating Token Index: 893

Text #8

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.4038. Min Act: -0.1700

Data Index: 5041554 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3845. Min Act: -0.1700

Data Index: 5589507 (Open Web Text)

Max Activating Token Index: 520

Text #10

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3439. Min Act: -0.1700

Data Index: 1501497 (Open Web Text)

Max Activating Token Index: 657

Text #11

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.4194. Min Act: -0.1700

Data Index: 4002182 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3754. Min Act: -0.1700

Data Index: 6110076 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3885. Min Act: -0.1700

Data Index: 169997 (Open Web Text)

Max Activating Token Index: 1014

Text #14

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3752. Min Act: -0.1700

Data Index: 5475040 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3868. Min Act: -0.1700

Data Index: 4305269 (Open Web Text)

Max Activating Token Index: 575

Text #16

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3710. Min Act: -0.1700

Data Index: 4211381 (Open Web Text)

Max Activating Token Index: 142

Text #17

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3581. Min Act: -0.1697

Data Index: 5763440 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.3802. Min Act: -0.1700

Data Index: 3138426 (Open Web Text)

Max Activating Token Index: 182

Text #19

Max Range: 4.6071. Min Range: -4.6071

Max Act: 4.2982. Min Act: -0.1700

Data Index: 1192608 (Open Web Text)

Max Activating Token Index: 871