Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 593 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1358229 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1011084 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0377. Min Act: -0.0002

Data Index: 443671 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0372. Min Act: -0.0002

Data Index: 979530 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0373. Min Act: -0.0002

Data Index: 177115 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0360. Min Act: -0.0003

Data Index: 751134 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0357. Min Act: -0.0002

Data Index: 351822 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1355115 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0359. Min Act: -0.0003

Data Index: 488131 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0360. Min Act: -0.0003

Data Index: 757810 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0359. Min Act: -0.0003

Data Index: 322761 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0348. Min Act: -0.0003

Data Index: 818442 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1269691 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0342. Min Act: -0.0002

Data Index: 972427 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0338. Min Act: -0.0002

Data Index: 414646 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0331. Min Act: -0.0003

Data Index: 737995 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1134676 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0328. Min Act: -0.0002

Data Index: 925339 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0323. Min Act: -0.0003

Data Index: 318150 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0319. Min Act: -0.0003

Data Index: 995584 (C4 (Web Text))

Max Activating Token Index: 209