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

Dataset: Open Web Text

Neuron 1200 in Layer 1

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: 1.8584. Min Range: -1.8584

Max Act: 1.8584. Min Act: -0.1700

Data Index: 3629316 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8531. Min Act: -0.1700

Data Index: 4416617 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8495. Min Act: -0.1700

Data Index: 1128014 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8435. Min Act: -0.1700

Data Index: 6123905 (Open Web Text)

Max Activating Token Index: 810

Text #4

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8500. Min Act: -0.1700

Data Index: 3608393 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8517. Min Act: -0.1700

Data Index: 5573944 (Open Web Text)

Max Activating Token Index: 623

Text #6

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8324. Min Act: -0.1700

Data Index: 3571261 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8416. Min Act: -0.1700

Data Index: 7442867 (Open Web Text)

Max Activating Token Index: 389

Text #8

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8451. Min Act: -0.1700

Data Index: 5462584 (Open Web Text)

Max Activating Token Index: 779

Text #9

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8260. Min Act: -0.1700

Data Index: 2011345 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8263. Min Act: -0.1700

Data Index: 2431898 (Open Web Text)

Max Activating Token Index: 354

Text #11

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8245. Min Act: -0.1700

Data Index: 5672104 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8173. Min Act: -0.1700

Data Index: 7680142 (Open Web Text)

Max Activating Token Index: 139

Text #13

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8291. Min Act: -0.1700

Data Index: 2067271 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8165. Min Act: -0.1700

Data Index: 1697536 (Open Web Text)

Max Activating Token Index: 45

Text #15

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8249. Min Act: -0.1700

Data Index: 2525152 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8087. Min Act: -0.1700

Data Index: 7544329 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8168. Min Act: -0.1700

Data Index: 2444730 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8141. Min Act: -0.1700

Data Index: 2838257 (Open Web Text)

Max Activating Token Index: 706

Text #19

Max Range: 1.8584. Min Range: -1.8584

Max Act: 1.8124. Min Act: -0.1700

Data Index: 6231504 (Open Web Text)

Max Activating Token Index: 665