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

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

Neuron 114 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4319. Min Range: -3.4319

Max Act: 3.4319. Min Act: -0.0000

Data Index: 336503 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.8234. Min Act: -0.0000

Data Index: 497187 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.9238. Min Act: -0.0000

Data Index: 1264978 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.6829. Min Act: -0.0000

Data Index: 140262 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.8955. Min Act: -0.0000

Data Index: 818842 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.7278. Min Act: -0.0000

Data Index: 633565 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.7019. Min Act: -0.0000

Data Index: 43670 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.4784. Min Act: -0.0000

Data Index: 209512 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.5517. Min Act: -0.0000

Data Index: 851366 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.6716. Min Act: -0.0000

Data Index: 114230 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.5116. Min Act: -0.0000

Data Index: 1590351 (Python Code)

Max Activating Token Index: 1018

Text #11

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.4913. Min Act: -0.0000

Data Index: 433817 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.5211. Min Act: -0.0000

Data Index: 1193321 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.4226. Min Act: -0.0000

Data Index: 519076 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.1208. Min Act: -0.0000

Data Index: 1534047 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1469393 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 3.4319. Min Range: -3.4319

Max Act: 2.1207. Min Act: -0.0000

Data Index: 1481746 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 3.4319. Min Range: -3.4319

Max Act: 1.9846. Min Act: -0.0000

Data Index: 207228 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 3.4319. Min Range: -3.4319

Max Act: 1.8790. Min Act: -0.0000

Data Index: 1020219 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 3.4319. Min Range: -3.4319

Max Act: 1.7692. Min Act: -0.0000

Data Index: 1215579 (C4 (Web Text))

Max Activating Token Index: 908