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

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

Neuron 155 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2893. Min Act: -0.0000

Data Index: 694005 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2477. Min Act: -0.0000

Data Index: 120674 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2427. Min Act: -0.0000

Data Index: 559016 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2435. Min Act: -0.0000

Data Index: 3885 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2372. Min Act: -0.0000

Data Index: 185072 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2346. Min Act: -0.0000

Data Index: 727145 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2459. Min Act: -0.0000

Data Index: 418094 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2285. Min Act: -0.0000

Data Index: 772243 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2411. Min Act: -0.0000

Data Index: 767840 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2304. Min Act: -0.0000

Data Index: 674523 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2324. Min Act: -0.0000

Data Index: 92863 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1231471 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1223646 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2298. Min Act: -0.0000

Data Index: 151286 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2215. Min Act: -0.0000

Data Index: 470332 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1041455 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2269. Min Act: -0.0000

Data Index: 170869 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1193699 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2149. Min Act: -0.0000

Data Index: 806756 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.2893. Min Range: -0.2893

Max Act: 0.2322. Min Act: -0.0000

Data Index: 777158 (C4 (Web Text))

Max Activating Token Index: 615