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

Dataset: Open Web Text

Neuron 20 in Layer 6

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: 3.5920. Min Range: -3.5920

Max Act: 3.5920. Min Act: -0.1700

Data Index: 4146555 (Open Web Text)

Max Activating Token Index: 288

Text #1

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.5351. Min Act: -0.1700

Data Index: 7882791 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.5293. Min Act: -0.1700

Data Index: 8643508 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4948. Min Act: -0.1700

Data Index: 7144525 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4893. Min Act: -0.1700

Data Index: 666917 (Open Web Text)

Max Activating Token Index: 376

Text #5

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4851. Min Act: -0.1700

Data Index: 6864744 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4868. Min Act: -0.1700

Data Index: 2494843 (Open Web Text)

Max Activating Token Index: 450

Text #7

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4900. Min Act: -0.1700

Data Index: 7772021 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4728. Min Act: -0.1700

Data Index: 6052829 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4383. Min Act: -0.1700

Data Index: 6472563 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1373270 (Open Web Text)

Max Activating Token Index: 970

Text #11

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4460. Min Act: -0.1700

Data Index: 5724900 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1564034 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4551. Min Act: -0.1700

Data Index: 2989000 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4386. Min Act: -0.1700

Data Index: 2385797 (Open Web Text)

Max Activating Token Index: 548

Text #15

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4155. Min Act: -0.1700

Data Index: 6462498 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4240. Min Act: -0.1700

Data Index: 5569835 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4108. Min Act: -0.1700

Data Index: 2426425 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4151. Min Act: -0.1700

Data Index: 2939216 (Open Web Text)

Max Activating Token Index: 314

Text #19

Max Range: 3.5920. Min Range: -3.5920

Max Act: 3.4138. Min Act: -0.1700

Data Index: 971192 (Open Web Text)

Max Activating Token Index: 811