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

Dataset: Open Web Text

Neuron 885 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: 3.0429. Min Range: -3.0429

Max Act: 3.0428. Min Act: -0.1700

Data Index: 1272432 (Open Web Text)

Max Activating Token Index: 871

Text #1

Max Range: 3.0429. Min Range: -3.0429

Max Act: 3.0429. Min Act: -0.1700

Data Index: 5617433 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 3.0429. Min Range: -3.0429

Max Act: 3.0317. Min Act: -0.1700

Data Index: 5667524 (Open Web Text)

Max Activating Token Index: 904

Text #3

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9905. Min Act: -0.1700

Data Index: 5645990 (Open Web Text)

Max Activating Token Index: 428

Text #4

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9803. Min Act: -0.1700

Data Index: 2142605 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9583. Min Act: -0.1700

Data Index: 2381210 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9667. Min Act: -0.1700

Data Index: 5734231 (Open Web Text)

Max Activating Token Index: 460

Text #7

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9681. Min Act: -0.1700

Data Index: 8336749 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9428. Min Act: -0.1700

Data Index: 5297598 (Open Web Text)

Max Activating Token Index: 200

Text #9

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9516. Min Act: -0.1700

Data Index: 1742635 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9346. Min Act: -0.1700

Data Index: 7797186 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9222. Min Act: -0.1700

Data Index: 6341259 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9319. Min Act: -0.1700

Data Index: 81507 (Open Web Text)

Max Activating Token Index: 546

Text #13

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9234. Min Act: -0.1700

Data Index: 408298 (Open Web Text)

Max Activating Token Index: 271

Text #14

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9108. Min Act: -0.1700

Data Index: 7841433 (Open Web Text)

Max Activating Token Index: 919

Text #15

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9025. Min Act: -0.1700

Data Index: 7671333 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9195. Min Act: -0.1700

Data Index: 5132625 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9060. Min Act: -0.1700

Data Index: 5421238 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9245. Min Act: -0.1700

Data Index: 7841426 (Open Web Text)

Max Activating Token Index: 544

Text #19

Max Range: 3.0429. Min Range: -3.0429

Max Act: 2.9167. Min Act: -0.1700

Data Index: 192746 (Open Web Text)

Max Activating Token Index: 416