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

Dataset: Open Web Text

Neuron 1679 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: 5.2373. Min Range: -5.2373

Max Act: 5.2266. Min Act: -0.1700

Data Index: 6788336 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.2373. Min Act: -0.1700

Data Index: 3752536 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.1264. Min Act: -0.1700

Data Index: 6658294 (Open Web Text)

Max Activating Token Index: 197

Text #3

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0900. Min Act: -0.1700

Data Index: 1312163 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0449. Min Act: -0.1700

Data Index: 7354540 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0354. Min Act: -0.1700

Data Index: 4402355 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0297. Min Act: -0.1700

Data Index: 3249045 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9915. Min Act: -0.1700

Data Index: 3752531 (Open Web Text)

Max Activating Token Index: 783

Text #8

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9871. Min Act: -0.1700

Data Index: 4983964 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0051. Min Act: -0.1700

Data Index: 5342592 (Open Web Text)

Max Activating Token Index: 854

Text #10

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9891. Min Act: -0.1700

Data Index: 282895 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 5.2373. Min Range: -5.2373

Max Act: 5.0176. Min Act: -0.1700

Data Index: 5256727 (Open Web Text)

Max Activating Token Index: 412

Text #12

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9780. Min Act: -0.1700

Data Index: 6194333 (Open Web Text)

Max Activating Token Index: 786

Text #13

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9766. Min Act: -0.1700

Data Index: 4648251 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9554. Min Act: -0.1700

Data Index: 1928808 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9535. Min Act: -0.1700

Data Index: 2416249 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9352. Min Act: -0.1700

Data Index: 1815763 (Open Web Text)

Max Activating Token Index: 340

Text #17

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9402. Min Act: -0.1700

Data Index: 1484850 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9201. Min Act: -0.1700

Data Index: 5750241 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 5.2373. Min Range: -5.2373

Max Act: 4.9215. Min Act: -0.1700

Data Index: 289306 (Open Web Text)

Max Activating Token Index: 742