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

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

Neuron 5043 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.4414. Min Act: -0.0000

Data Index: 590341 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.4116. Min Act: -0.0000

Data Index: 998565 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.4263. Min Act: -0.0000

Data Index: 698469 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1111711 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.4083. Min Act: -0.0000

Data Index: 972581 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.4225. Min Act: -0.0000

Data Index: 108227 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3937. Min Act: -0.0000

Data Index: 931803 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3896. Min Act: -0.0000

Data Index: 404008 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1314489 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3614. Min Act: -0.0000

Data Index: 323282 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3449. Min Act: -0.0000

Data Index: 381225 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3637. Min Act: -0.0000

Data Index: 641777 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1214508 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1323776 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3756. Min Act: -0.0000

Data Index: 258606 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3322. Min Act: -0.0000

Data Index: 167773 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1014134 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3380. Min Act: -0.0000

Data Index: 527133 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3378. Min Act: -0.0000

Data Index: 948421 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.4414. Min Range: -0.4414

Max Act: 0.3257. Min Act: -0.0000

Data Index: 354526 (C4 (Web Text))

Max Activating Token Index: 585