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

Dataset: Open Web Text

Neuron 2720 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: 2.8271. Min Range: -2.8271

Max Act: 2.8109. Min Act: -0.1700

Data Index: 8754004 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7513. Min Act: -0.1700

Data Index: 7931092 (Open Web Text)

Max Activating Token Index: 287

Text #2

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7528. Min Act: -0.1700

Data Index: 6741922 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.8271. Min Act: -0.1700

Data Index: 5957757 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.8256. Min Act: -0.1700

Data Index: 4194602 (Open Web Text)

Max Activating Token Index: 479

Text #5

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7518. Min Act: -0.1700

Data Index: 6926929 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7644. Min Act: -0.1700

Data Index: 3884427 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7203. Min Act: -0.1700

Data Index: 4044421 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7391. Min Act: -0.1700

Data Index: 2261734 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7042. Min Act: -0.1700

Data Index: 1890171 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7291. Min Act: -0.1700

Data Index: 4645377 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7117. Min Act: -0.1700

Data Index: 6775245 (Open Web Text)

Max Activating Token Index: 1021

Text #12

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7003. Min Act: -0.1700

Data Index: 4895797 (Open Web Text)

Max Activating Token Index: 187

Text #13

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7396. Min Act: -0.1700

Data Index: 6994709 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7388. Min Act: -0.1700

Data Index: 4057953 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7036. Min Act: -0.1700

Data Index: 8183160 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7305. Min Act: -0.1700

Data Index: 8642884 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7196. Min Act: -0.1700

Data Index: 6773485 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.6807. Min Act: -0.1700

Data Index: 3942131 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 2.8271. Min Range: -2.8271

Max Act: 2.7178. Min Act: -0.1700

Data Index: 5886442 (Open Web Text)

Max Activating Token Index: 10