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

Dataset: Open Web Text

Neuron 2514 in Layer 3

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: 4.4362. Min Range: -4.4362

Max Act: 4.4362. Min Act: -0.1700

Data Index: 2914957 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3364. Min Act: -0.1700

Data Index: 416922 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3636. Min Act: -0.1700

Data Index: 3217198 (Open Web Text)

Max Activating Token Index: 512

Text #3

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3285. Min Act: -0.1700

Data Index: 4284575 (Open Web Text)

Max Activating Token Index: 757

Text #4

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3514. Min Act: -0.1700

Data Index: 8151937 (Open Web Text)

Max Activating Token Index: 771

Text #5

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3516. Min Act: -0.1700

Data Index: 5958326 (Open Web Text)

Max Activating Token Index: 556

Text #6

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3190. Min Act: -0.1700

Data Index: 6131027 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.4219. Min Act: -0.1700

Data Index: 1975710 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2972. Min Act: -0.1700

Data Index: 5954946 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3527. Min Act: -0.1700

Data Index: 8136958 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3221. Min Act: -0.1700

Data Index: 1975711 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3223. Min Act: -0.1700

Data Index: 8628156 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3356. Min Act: -0.1700

Data Index: 535685 (Open Web Text)

Max Activating Token Index: 796

Text #13

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3249. Min Act: -0.1700

Data Index: 7718581 (Open Web Text)

Max Activating Token Index: 244

Text #14

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2383. Min Act: -0.1700

Data Index: 4295069 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3446. Min Act: -0.1700

Data Index: 6597622 (Open Web Text)

Max Activating Token Index: 831

Text #16

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3137. Min Act: -0.1700

Data Index: 5316808 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2858. Min Act: -0.1700

Data Index: 2204408 (Open Web Text)

Max Activating Token Index: 786

Text #18

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.3556. Min Act: -0.1700

Data Index: 4935579 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 4.4362. Min Range: -4.4362

Max Act: 4.2613. Min Act: -0.1700

Data Index: 506224 (Open Web Text)

Max Activating Token Index: 570