Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 643 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0006

Data Index: 223974 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0323. Min Act: -0.0006

Data Index: 373228 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0322. Min Act: -0.0006

Data Index: 1050528 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0318. Min Act: -0.0006

Data Index: 448823 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1084353 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0304. Min Act: -0.0006

Data Index: 427384 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0302. Min Act: -0.0006

Data Index: 46547 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0304. Min Act: -0.0006

Data Index: 845495 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0302. Min Act: -0.0006

Data Index: 530869 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0295. Min Act: -0.0006

Data Index: 821442 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1059658 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0293. Min Act: -0.0006

Data Index: 731743 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1247672 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1028222 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0286. Min Act: -0.0006

Data Index: 535116 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0290. Min Act: -0.0006

Data Index: 641946 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0291. Min Act: -0.0006

Data Index: 246658 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0290. Min Act: -0.0006

Data Index: 522238 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0290. Min Act: -0.0006

Data Index: 17804 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0287. Min Act: -0.0006

Data Index: 104558 (C4 (Web Text))

Max Activating Token Index: 301