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

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

Neuron 4174 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0354. Min Act: -0.0003

Data Index: 531703 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0003

Data Index: 761812 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0332. Min Act: -0.0003

Data Index: 686004 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0340. Min Act: -0.0003

Data Index: 863179 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0345. Min Act: -0.0003

Data Index: 393110 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1354974 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0307. Min Act: -0.0003

Data Index: 601943 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0310. Min Act: -0.0002

Data Index: 568287 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0322. Min Act: -0.0002

Data Index: 170519 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0250. Min Act: -0.0003

Data Index: 713270 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0297. Min Act: -0.0003

Data Index: 219770 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0312. Min Act: -0.0003

Data Index: 106543 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1061504 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1197912 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0003

Data Index: 928220 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0315. Min Act: -0.0002

Data Index: 589136 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1337640 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0003

Data Index: 511885 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1026393 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0267. Min Act: -0.0003

Data Index: 657816 (C4 (Web Text))

Max Activating Token Index: 38