Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 235 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0006

Data Index: 917745 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0464. Min Act: -0.0006

Data Index: 801833 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0450. Min Act: -0.0006

Data Index: 754245 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0441. Min Act: -0.0006

Data Index: 487447 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0444. Min Act: -0.0006

Data Index: 1326675 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0406. Min Act: -0.0005

Data Index: 568142 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1251068 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0405. Min Act: -0.0006

Data Index: 70951 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0401. Min Act: -0.0006

Data Index: 95716 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0367. Min Act: -0.0006

Data Index: 866122 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1096839 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0395. Min Act: -0.0006

Data Index: 703749 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0392. Min Act: -0.0006

Data Index: 120923 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0392. Min Act: -0.0006

Data Index: 919308 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0383. Min Act: -0.0006

Data Index: 751196 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0380. Min Act: -0.0006

Data Index: 363210 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0390. Min Act: -0.0006

Data Index: 492166 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0374. Min Act: -0.0006

Data Index: 84887 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0374. Min Act: -0.0006

Data Index: 709308 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0372. Min Act: -0.0006

Data Index: 603266 (C4 (Web Text))

Max Activating Token Index: 971