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

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

Neuron 833 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.8421. Min Act: -0.0001

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6941. Min Act: -0.0001

Data Index: 169628 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.7584. Min Act: -0.0001

Data Index: 27537 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6970. Min Act: -0.0001

Data Index: 1028727 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6912. Min Act: -0.0001

Data Index: 722258 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6308. Min Act: -0.0001

Data Index: 690609 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6976. Min Act: -0.0001

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.4978. Min Act: -0.0001

Data Index: 1070095 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5799. Min Act: -0.0001

Data Index: 725178 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6613. Min Act: -0.0001

Data Index: 180672 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5741. Min Act: -0.0001

Data Index: 737263 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5954. Min Act: -0.0001

Data Index: 424398 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6245. Min Act: -0.0001

Data Index: 960327 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5918. Min Act: -0.0001

Data Index: 669442 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6365. Min Act: -0.0001

Data Index: 1183659 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5565. Min Act: -0.0001

Data Index: 1136477 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.6262. Min Act: -0.0001

Data Index: 240777 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5259. Min Act: -0.0001

Data Index: 1229221 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.5291. Min Act: -0.0001

Data Index: 582281 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.8421. Min Range: -1.8421

Max Act: 1.4418. Min Act: -0.0001

Data Index: 412227 (C4 (Web Text))

Max Activating Token Index: 80