Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5059 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7519. Min Act: -0.0000

Data Index: 835944 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8234. Min Act: -0.0000

Data Index: 244474 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.8222. Min Act: -0.0000

Data Index: 697297 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7216. Min Act: -0.0000

Data Index: 382052 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7595. Min Act: -0.0000

Data Index: 277692 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1415612 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7181. Min Act: -0.0000

Data Index: 86645 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7192. Min Act: -0.0000

Data Index: 681203 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7100. Min Act: -0.0000

Data Index: 201919 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6744. Min Act: -0.0000

Data Index: 171293 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.7001. Min Act: -0.0000

Data Index: 283874 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6377. Min Act: -0.0000

Data Index: 474770 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5314. Min Act: -0.0000

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6579. Min Act: -0.0000

Data Index: 295714 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5405. Min Act: -0.0000

Data Index: 8227 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1261921 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5907. Min Act: -0.0000

Data Index: 591576 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5626. Min Act: -0.0000

Data Index: 330000 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.6622. Min Act: -0.0000

Data Index: 212542 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.8234. Min Range: -0.8234

Max Act: 0.5896. Min Act: -0.0000

Data Index: 90409 (C4 (Web Text))

Max Activating Token Index: 10