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

Dataset: Open Web Text

Neuron 275 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: 6.2363. Min Range: -6.2363

Max Act: 6.2363. Min Act: -0.1700

Data Index: 4980563 (Open Web Text)

Max Activating Token Index: 530

Text #1

Max Range: 6.2363. Min Range: -6.2363

Max Act: 6.1997. Min Act: -0.1700

Data Index: 7900302 (Open Web Text)

Max Activating Token Index: 854

Text #2

Max Range: 6.2363. Min Range: -6.2363

Max Act: 6.0636. Min Act: -0.1700

Data Index: 6378730 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 6.2363. Min Range: -6.2363

Max Act: 6.0415. Min Act: -0.1700

Data Index: 3160733 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 6.2363. Min Range: -6.2363

Max Act: 6.0203. Min Act: -0.1700

Data Index: 1692554 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 6.2363. Min Range: -6.2363

Max Act: 6.0109. Min Act: -0.1700

Data Index: 3257168 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.9382. Min Act: -0.1700

Data Index: 290630 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.9304. Min Act: -0.1700

Data Index: 6748521 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.9289. Min Act: -0.1700

Data Index: 7459612 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.9354. Min Act: -0.1700

Data Index: 4965707 (Open Web Text)

Max Activating Token Index: 272

Text #10

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8794. Min Act: -0.1699

Data Index: 2424066 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8565. Min Act: -0.1700

Data Index: 3512668 (Open Web Text)

Max Activating Token Index: 506

Text #12

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8658. Min Act: -0.1700

Data Index: 6378021 (Open Web Text)

Max Activating Token Index: 333

Text #13

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8816. Min Act: -0.1700

Data Index: 1481172 (Open Web Text)

Max Activating Token Index: 572

Text #14

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8300. Min Act: -0.1700

Data Index: 2272470 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8407. Min Act: -0.1700

Data Index: 835655 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.9086. Min Act: -0.1700

Data Index: 8177397 (Open Web Text)

Max Activating Token Index: 857

Text #17

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8307. Min Act: -0.1700

Data Index: 4679497 (Open Web Text)

Max Activating Token Index: 411

Text #18

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8518. Min Act: -0.1700

Data Index: 6173952 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 6.2363. Min Range: -6.2363

Max Act: 5.8157. Min Act: -0.1700

Data Index: 3997313 (Open Web Text)

Max Activating Token Index: 591