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

Dataset: Open Web Text

Neuron 2203 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: 3.9959. Min Range: -3.9959

Max Act: 3.9704. Min Act: -0.1700

Data Index: 7945899 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.9959. Min Act: -0.1700

Data Index: 5502067 (Open Web Text)

Max Activating Token Index: 494

Text #2

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.9542. Min Act: -0.1700

Data Index: 4055912 (Open Web Text)

Max Activating Token Index: 155

Text #3

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8959. Min Act: -0.1700

Data Index: 4516049 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8723. Min Act: -0.1700

Data Index: 5134334 (Open Web Text)

Max Activating Token Index: 143

Text #5

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8897. Min Act: -0.1700

Data Index: 1586834 (Open Web Text)

Max Activating Token Index: 404

Text #6

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8541. Min Act: -0.1700

Data Index: 2607068 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8764. Min Act: -0.1700

Data Index: 8017387 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8715. Min Act: -0.1700

Data Index: 7341903 (Open Web Text)

Max Activating Token Index: 93

Text #9

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8472. Min Act: -0.1700

Data Index: 2374868 (Open Web Text)

Max Activating Token Index: 438

Text #10

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8337. Min Act: -0.1700

Data Index: 2666361 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8353. Min Act: -0.1700

Data Index: 8389381 (Open Web Text)

Max Activating Token Index: 174

Text #12

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8210. Min Act: -0.1700

Data Index: 514023 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8122. Min Act: -0.1700

Data Index: 7570268 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8097. Min Act: -0.1700

Data Index: 5018617 (Open Web Text)

Max Activating Token Index: 933

Text #15

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8159. Min Act: -0.1700

Data Index: 8790364 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.7905. Min Act: -0.1700

Data Index: 4237607 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.8004. Min Act: -0.1700

Data Index: 7184582 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.7965. Min Act: -0.1700

Data Index: 5589762 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 3.9959. Min Range: -3.9959

Max Act: 3.7677. Min Act: -0.1700

Data Index: 39705 (Open Web Text)

Max Activating Token Index: 987