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

Dataset: Open Web Text

Neuron 2222 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: 3.0670. Min Range: -3.0670

Max Act: 3.0670. Min Act: -0.1700

Data Index: 2390967 (Open Web Text)

Max Activating Token Index: 242

Text #1

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0416. Min Act: -0.1700

Data Index: 5348958 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0385. Min Act: -0.1700

Data Index: 464471 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0376. Min Act: -0.1700

Data Index: 1482703 (Open Web Text)

Max Activating Token Index: 208

Text #4

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0373. Min Act: -0.1700

Data Index: 6230527 (Open Web Text)

Max Activating Token Index: 816

Text #5

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0254. Min Act: -0.1700

Data Index: 5912075 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0257. Min Act: -0.1700

Data Index: 6574216 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0230. Min Act: -0.1700

Data Index: 6277236 (Open Web Text)

Max Activating Token Index: 928

Text #8

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9518. Min Act: -0.1700

Data Index: 235579 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9499. Min Act: -0.1700

Data Index: 2398091 (Open Web Text)

Max Activating Token Index: 904

Text #10

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9900. Min Act: -0.1700

Data Index: 5519292 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 3.0670. Min Range: -3.0670

Max Act: 3.0072. Min Act: -0.1700

Data Index: 2960932 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9829. Min Act: -0.1700

Data Index: 8559581 (Open Web Text)

Max Activating Token Index: 295

Text #13

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9637. Min Act: -0.1700

Data Index: 4822898 (Open Web Text)

Max Activating Token Index: 421

Text #14

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9668. Min Act: -0.1700

Data Index: 8738920 (Open Web Text)

Max Activating Token Index: 613

Text #15

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9678. Min Act: -0.1700

Data Index: 6566838 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9608. Min Act: -0.1700

Data Index: 629917 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9375. Min Act: -0.1700

Data Index: 4363747 (Open Web Text)

Max Activating Token Index: 164

Text #18

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9238. Min Act: -0.1700

Data Index: 1306651 (Open Web Text)

Max Activating Token Index: 605

Text #19

Max Range: 3.0670. Min Range: -3.0670

Max Act: 2.9519. Min Act: -0.1700

Data Index: 7088473 (Open Web Text)

Max Activating Token Index: 425