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

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

Neuron 1922 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.8123. Min Act: -0.0000

Data Index: 77439 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.6718. Min Act: -0.0000

Data Index: 1230363 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.6812. Min Act: -0.0000

Data Index: 378780 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.5007. Min Act: -0.0000

Data Index: 1319031 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.6244. Min Act: -0.0000

Data Index: 1221973 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.4785. Min Act: -0.0000

Data Index: 871723 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.7100. Min Act: -0.0000

Data Index: 852271 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.4373. Min Act: 0.0000

Data Index: 1169866 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.4370. Min Act: -0.0000

Data Index: 391895 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.4337. Min Act: 0.0000

Data Index: 591552 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.4510. Min Act: -0.0000

Data Index: 232177 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.1775. Min Act: 0.0000

Data Index: 710979 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.1288. Min Act: -0.0000

Data Index: 1187826 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.2515. Min Act: 0.0000

Data Index: 589717 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.1222. Min Act: -0.0000

Data Index: 257400 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.1188. Min Act: 0.0000

Data Index: 116659 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.1151. Min Act: 0.0000

Data Index: 150711 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.0031. Min Act: -0.0000

Data Index: 552930 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 2.8123. Min Range: -2.8123

Max Act: 2.1041. Min Act: 0.0000

Data Index: 1286676 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 2.8123. Min Range: -2.8123

Max Act: 1.9786. Min Act: -0.0000

Data Index: 551697 (C4 (Web Text))

Max Activating Token Index: 293