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

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

Neuron 6044 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0002

Data Index: 602599 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0380. Min Act: -0.0002

Data Index: 957601 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0393. Min Act: -0.0002

Data Index: 826306 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0376. Min Act: -0.0002

Data Index: 806487 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0357. Min Act: -0.0002

Data Index: 604131 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0357. Min Act: -0.0002

Data Index: 631727 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0358. Min Act: -0.0002

Data Index: 535753 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0357. Min Act: -0.0002

Data Index: 554096 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0341. Min Act: -0.0002

Data Index: 565358 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1246016 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0345. Min Act: -0.0002

Data Index: 969054 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0344. Min Act: -0.0002

Data Index: 675563 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0339. Min Act: -0.0002

Data Index: 894891 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0346. Min Act: -0.0002

Data Index: 626300 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0339. Min Act: -0.0002

Data Index: 974176 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0336. Min Act: -0.0002

Data Index: 7500 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0320. Min Act: -0.0002

Data Index: 244640 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0327. Min Act: -0.0002

Data Index: 306086 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0312. Min Act: -0.0002

Data Index: 818870 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0330. Min Act: -0.0002

Data Index: 1254383 (C4 (Web Text))

Max Activating Token Index: 1002