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

Dataset: Open Web Text

Neuron 1024 in Layer 0

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: 7.6264. Min Range: -7.6264

Max Act: 7.6264. Min Act: -0.1700

Data Index: 2424342 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 7.6264. Min Range: -7.6264

Max Act: 7.2129. Min Act: -0.1700

Data Index: 3124171 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 7.6264. Min Range: -7.6264

Max Act: 7.2356. Min Act: -0.1700

Data Index: 587703 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.7353. Min Act: -0.1700

Data Index: 13791 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.7432. Min Act: -0.1700

Data Index: 4349014 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.6044. Min Act: -0.1700

Data Index: 8179383 (Open Web Text)

Max Activating Token Index: 265

Text #6

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5978. Min Act: -0.1700

Data Index: 6254291 (Open Web Text)

Max Activating Token Index: 31

Text #7

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5756. Min Act: -0.1700

Data Index: 1268543 (Open Web Text)

Max Activating Token Index: 418

Text #8

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.6343. Min Act: -0.1700

Data Index: 6071844 (Open Web Text)

Max Activating Token Index: 40

Text #9

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5788. Min Act: -0.1700

Data Index: 4943893 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.6332. Min Act: -0.1700

Data Index: 3074462 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5360. Min Act: -0.1700

Data Index: 3191001 (Open Web Text)

Max Activating Token Index: 225

Text #12

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5133. Min Act: -0.1700

Data Index: 3103343 (Open Web Text)

Max Activating Token Index: 70

Text #13

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5357. Min Act: -0.1685

Data Index: 3009227 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5368. Min Act: -0.1700

Data Index: 7928618 (Open Web Text)

Max Activating Token Index: 355

Text #15

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5532. Min Act: -0.1700

Data Index: 8690590 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5261. Min Act: -0.1700

Data Index: 3731164 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.5250. Min Act: -0.1700

Data Index: 8308102 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.4961. Min Act: -0.1700

Data Index: 2317216 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 7.6264. Min Range: -7.6264

Max Act: 6.4682. Min Act: -0.1700

Data Index: 7976948 (Open Web Text)

Max Activating Token Index: 540