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

Dataset: Open Web Text

Neuron 196 in Layer 5

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: 4.6335. Min Range: -4.6335

Max Act: 4.6287. Min Act: -0.1700

Data Index: 4638223 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.6335. Min Act: -0.1700

Data Index: 2397717 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.5909. Min Act: -0.1700

Data Index: 1304675 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.5473. Min Act: -0.1700

Data Index: 7378272 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.5379. Min Act: -0.1700

Data Index: 206001 (Open Web Text)

Max Activating Token Index: 177

Text #5

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.5176. Min Act: -0.1700

Data Index: 3135479 (Open Web Text)

Max Activating Token Index: 190

Text #6

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.5193. Min Act: -0.1700

Data Index: 6871172 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4992. Min Act: -0.1700

Data Index: 6801643 (Open Web Text)

Max Activating Token Index: 385

Text #8

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4546. Min Act: -0.1700

Data Index: 986851 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4078. Min Act: -0.1700

Data Index: 3058791 (Open Web Text)

Max Activating Token Index: 752

Text #10

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4475. Min Act: -0.1700

Data Index: 8289857 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.4067. Min Act: -0.1700

Data Index: 6115702 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3098. Min Act: -0.1700

Data Index: 5120561 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3904. Min Act: -0.1700

Data Index: 557873 (Open Web Text)

Max Activating Token Index: 157

Text #14

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3334. Min Act: -0.1700

Data Index: 4478764 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3695. Min Act: -0.1700

Data Index: 3341532 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3234. Min Act: -0.1700

Data Index: 6927922 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3357. Min Act: -0.1700

Data Index: 1444043 (Open Web Text)

Max Activating Token Index: 760

Text #18

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.2588. Min Act: -0.1700

Data Index: 3250125 (Open Web Text)

Max Activating Token Index: 345

Text #19

Max Range: 4.6335. Min Range: -4.6335

Max Act: 4.3133. Min Act: -0.1700

Data Index: 1728620 (Open Web Text)

Max Activating Token Index: 470