Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1212 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0005

Data Index: 1096350 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0395. Min Act: -0.0005

Data Index: 1325473 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0394. Min Act: -0.0005

Data Index: 733662 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0392. Min Act: -0.0005

Data Index: 7747 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0397. Min Act: -0.0005

Data Index: 398907 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0392. Min Act: -0.0005

Data Index: 380161 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0383. Min Act: -0.0005

Data Index: 358996 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0353. Min Act: -0.0005

Data Index: 515195 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0364. Min Act: -0.0005

Data Index: 202366 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0362. Min Act: -0.0005

Data Index: 743849 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0364. Min Act: -0.0005

Data Index: 926311 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0371. Min Act: -0.0005

Data Index: 828414 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0353. Min Act: -0.0005

Data Index: 686497 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0347. Min Act: -0.0005

Data Index: 1198205 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0354. Min Act: -0.0005

Data Index: 987555 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0345. Min Act: -0.0005

Data Index: 236748 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0337. Min Act: -0.0005

Data Index: 675370 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0358. Min Act: -0.0005

Data Index: 267103 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0357. Min Act: -0.0005

Data Index: 916097 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0338. Min Act: -0.0005

Data Index: 773389 (C4 (Web Text))

Max Activating Token Index: 997