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

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

Neuron 4469 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0003

Data Index: 60273 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0409. Min Act: -0.0003

Data Index: 78549 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0380. Min Act: -0.0003

Data Index: 668727 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0003

Data Index: 225710 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1004525 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0341. Min Act: -0.0003

Data Index: 348942 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1004287 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0337. Min Act: -0.0003

Data Index: 456453 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0336. Min Act: -0.0003

Data Index: 932335 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0335. Min Act: -0.0003

Data Index: 201105 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0333. Min Act: -0.0003

Data Index: 750344 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1003236 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0338. Min Act: -0.0003

Data Index: 754767 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0328. Min Act: -0.0003

Data Index: 365860 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0321. Min Act: -0.0003

Data Index: 534718 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0327. Min Act: -0.0003

Data Index: 705754 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1117008 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1002051 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0319. Min Act: -0.0003

Data Index: 651162 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0319. Min Act: -0.0002

Data Index: 350158 (C4 (Web Text))

Max Activating Token Index: 206