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

Dataset: Open Web Text

Neuron 1849 in Layer 3

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: 1.9344. Min Range: -1.9344

Max Act: 1.9344. Min Act: -0.1700

Data Index: 5049460 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.8420. Min Act: -0.1700

Data Index: 2751703 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.8447. Min Act: -0.1700

Data Index: 2559960 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.8323. Min Act: -0.1700

Data Index: 1731051 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7889. Min Act: -0.1700

Data Index: 8050904 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7935. Min Act: -0.1700

Data Index: 7547895 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7959. Min Act: -0.1700

Data Index: 2706892 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7774. Min Act: -0.1700

Data Index: 809547 (Open Web Text)

Max Activating Token Index: 252

Text #8

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7840. Min Act: -0.1700

Data Index: 3566369 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7733. Min Act: -0.1700

Data Index: 6888378 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7510. Min Act: -0.1700

Data Index: 1917030 (Open Web Text)

Max Activating Token Index: 148

Text #11

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7606. Min Act: -0.1700

Data Index: 6695284 (Open Web Text)

Max Activating Token Index: 260

Text #12

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7411. Min Act: -0.1700

Data Index: 3434486 (Open Web Text)

Max Activating Token Index: 148

Text #13

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7224. Min Act: -0.1700

Data Index: 7547898 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7362. Min Act: -0.1700

Data Index: 1396953 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7142. Min Act: -0.1700

Data Index: 5076820 (Open Web Text)

Max Activating Token Index: 930

Text #16

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7278. Min Act: -0.1700

Data Index: 2804405 (Open Web Text)

Max Activating Token Index: 1014

Text #17

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7200. Min Act: -0.1700

Data Index: 1467577 (Open Web Text)

Max Activating Token Index: 381

Text #18

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.6949. Min Act: -0.1700

Data Index: 628244 (Open Web Text)

Max Activating Token Index: 502

Text #19

Max Range: 1.9344. Min Range: -1.9344

Max Act: 1.7268. Min Act: -0.1700

Data Index: 7547897 (Open Web Text)

Max Activating Token Index: 691