Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2218 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0002

Data Index: 122169 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0330. Min Act: -0.0002

Data Index: 743040 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0326. Min Act: -0.0002

Data Index: 735064 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0326. Min Act: -0.0002

Data Index: 824294 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1134739 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0320. Min Act: -0.0002

Data Index: 690194 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0318. Min Act: -0.0002

Data Index: 169013 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1329405 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1106138 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0313. Min Act: -0.0002

Data Index: 350084 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0312. Min Act: -0.0002

Data Index: 248605 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0312. Min Act: -0.0002

Data Index: 417273 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0308. Min Act: -0.0002

Data Index: 518792 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0308. Min Act: -0.0002

Data Index: 844036 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0306. Min Act: -0.0002

Data Index: 305585 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0300. Min Act: -0.0002

Data Index: 221769 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0305. Min Act: -0.0002

Data Index: 528694 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0305. Min Act: -0.0002

Data Index: 793252 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0304. Min Act: -0.0002

Data Index: 678221 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0302. Min Act: -0.0002

Data Index: 631358 (C4 (Web Text))

Max Activating Token Index: 142