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

Dataset: Open Web Text

Neuron 2508 in Layer 2

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: 5.1466. Min Range: -5.1466

Max Act: 5.1387. Min Act: -0.1700

Data Index: 2467468 (Open Web Text)

Max Activating Token Index: 838

Text #1

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.1466. Min Act: -0.1700

Data Index: 2256319 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.1315. Min Act: -0.1700

Data Index: 5475388 (Open Web Text)

Max Activating Token Index: 999

Text #3

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.1264. Min Act: -0.1700

Data Index: 3383176 (Open Web Text)

Max Activating Token Index: 430

Text #4

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.0808. Min Act: -0.1700

Data Index: 4251714 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.0739. Min Act: -0.1700

Data Index: 1900243 (Open Web Text)

Max Activating Token Index: 441

Text #6

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.0107. Min Act: -0.1700

Data Index: 2458358 (Open Web Text)

Max Activating Token Index: 764

Text #7

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.0232. Min Act: -0.1700

Data Index: 5064522 (Open Web Text)

Max Activating Token Index: 923

Text #8

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.0394. Min Act: -0.1700

Data Index: 1909174 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9921. Min Act: -0.1700

Data Index: 3520866 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9816. Min Act: -0.1700

Data Index: 6219138 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9751. Min Act: -0.1700

Data Index: 406462 (Open Web Text)

Max Activating Token Index: 434

Text #12

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9972. Min Act: -0.1700

Data Index: 4274189 (Open Web Text)

Max Activating Token Index: 494

Text #13

Max Range: 5.1466. Min Range: -5.1466

Max Act: 5.0043. Min Act: -0.1700

Data Index: 4651328 (Open Web Text)

Max Activating Token Index: 357

Text #14

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9661. Min Act: -0.1700

Data Index: 74277 (Open Web Text)

Max Activating Token Index: 854

Text #15

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9341. Min Act: -0.1700

Data Index: 5081165 (Open Web Text)

Max Activating Token Index: 623

Text #16

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9424. Min Act: -0.1700

Data Index: 5360362 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9500. Min Act: -0.1700

Data Index: 3160059 (Open Web Text)

Max Activating Token Index: 464

Text #18

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9434. Min Act: -0.1700

Data Index: 4752141 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 5.1466. Min Range: -5.1466

Max Act: 4.9774. Min Act: -0.1700

Data Index: 6847284 (Open Web Text)

Max Activating Token Index: 397