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

Dataset: Open Web Text

Neuron 1764 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: 5.3265. Min Range: -5.3265

Max Act: 5.3265. Min Act: -0.1700

Data Index: 6718119 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.2258. Min Act: -0.1700

Data Index: 4916707 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1502. Min Act: -0.1700

Data Index: 7539818 (Open Web Text)

Max Activating Token Index: 629

Text #3

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1653. Min Act: -0.1700

Data Index: 5264959 (Open Web Text)

Max Activating Token Index: 614

Text #4

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1287. Min Act: -0.1700

Data Index: 4340964 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1227. Min Act: -0.1700

Data Index: 1420954 (Open Web Text)

Max Activating Token Index: 631

Text #6

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1180. Min Act: -0.1700

Data Index: 4070676 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1498. Min Act: -0.1700

Data Index: 7088419 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.1428. Min Act: -0.1700

Data Index: 1078307 (Open Web Text)

Max Activating Token Index: 703

Text #9

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0793. Min Act: -0.1700

Data Index: 4962628 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0610. Min Act: -0.1700

Data Index: 6532342 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0951. Min Act: -0.1700

Data Index: 5835968 (Open Web Text)

Max Activating Token Index: 759

Text #12

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0483. Min Act: -0.1700

Data Index: 1538451 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0498. Min Act: -0.1700

Data Index: 5867340 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0301. Min Act: -0.1700

Data Index: 3974492 (Open Web Text)

Max Activating Token Index: 318

Text #15

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0444. Min Act: -0.1700

Data Index: 714699 (Open Web Text)

Max Activating Token Index: 627

Text #16

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0376. Min Act: -0.1700

Data Index: 2709683 (Open Web Text)

Max Activating Token Index: 635

Text #17

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0538. Min Act: -0.1700

Data Index: 4317259 (Open Web Text)

Max Activating Token Index: 564

Text #18

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0389. Min Act: -0.1700

Data Index: 2846371 (Open Web Text)

Max Activating Token Index: 660

Text #19

Max Range: 5.3265. Min Range: -5.3265

Max Act: 5.0039. Min Act: -0.1700

Data Index: 5814921 (Open Web Text)

Max Activating Token Index: 391