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

Dataset: Open Web Text

Neuron 1952 in Layer 5

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: 4.2359. Min Range: -4.2359

Max Act: 4.2122. Min Act: -0.1700

Data Index: 2041979 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1969. Min Act: -0.1700

Data Index: 8577592 (Open Web Text)

Max Activating Token Index: 765

Text #2

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.2023. Min Act: -0.1700

Data Index: 7714436 (Open Web Text)

Max Activating Token Index: 260

Text #3

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.2031. Min Act: -0.1700

Data Index: 5935838 (Open Web Text)

Max Activating Token Index: 752

Text #4

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.2359. Min Act: -0.1700

Data Index: 5924770 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.2264. Min Act: -0.1700

Data Index: 5476445 (Open Web Text)

Max Activating Token Index: 301

Text #6

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.2066. Min Act: -0.1700

Data Index: 8758376 (Open Web Text)

Max Activating Token Index: 895

Text #7

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1990. Min Act: -0.1700

Data Index: 7923378 (Open Web Text)

Max Activating Token Index: 1016

Text #8

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1927. Min Act: -0.1700

Data Index: 3999133 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1820. Min Act: -0.1700

Data Index: 558893 (Open Web Text)

Max Activating Token Index: 129

Text #10

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.2270. Min Act: -0.1700

Data Index: 5189941 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1515. Min Act: -0.1700

Data Index: 6027692 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1832. Min Act: -0.1700

Data Index: 6120449 (Open Web Text)

Max Activating Token Index: 269

Text #13

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1674. Min Act: -0.1700

Data Index: 2975324 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1301. Min Act: -0.1700

Data Index: 5341879 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1350. Min Act: -0.1700

Data Index: 5319805 (Open Web Text)

Max Activating Token Index: 278

Text #16

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1386. Min Act: -0.1700

Data Index: 4840269 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1378. Min Act: -0.1700

Data Index: 8319734 (Open Web Text)

Max Activating Token Index: 671

Text #18

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1192. Min Act: -0.1700

Data Index: 7305382 (Open Web Text)

Max Activating Token Index: 384

Text #19

Max Range: 4.2359. Min Range: -4.2359

Max Act: 4.1247. Min Act: -0.1700

Data Index: 6488317 (Open Web Text)

Max Activating Token Index: 145