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

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

Neuron 1613 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6993. Min Act: -0.0003

Data Index: 1246194 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6196. Min Act: -0.0003

Data Index: 904099 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6213. Min Act: -0.0002

Data Index: 1159373 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.6027. Min Act: -0.0002

Data Index: 35363 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5814. Min Act: -0.0003

Data Index: 109293 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5814. Min Act: -0.0003

Data Index: 395709 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5797. Min Act: -0.0002

Data Index: 153659 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5633. Min Act: -0.0003

Data Index: 1225581 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5364. Min Act: -0.0002

Data Index: 1213684 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5507. Min Act: -0.0002

Data Index: 413847 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5465. Min Act: -0.0003

Data Index: 1207259 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5469. Min Act: -0.0002

Data Index: 1173947 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5276. Min Act: -0.0002

Data Index: 3071 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5309. Min Act: -0.0002

Data Index: 605982 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.4820. Min Act: -0.0003

Data Index: 1150977 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5283. Min Act: -0.0002

Data Index: 334825 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5237. Min Act: -0.0002

Data Index: 910394 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.4928. Min Act: -0.0003

Data Index: 556823 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5174. Min Act: -0.0002

Data Index: 576201 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.6993. Min Range: -0.6993

Max Act: 0.5186. Min Act: -0.0002

Data Index: 345711 (C4 (Web Text))

Max Activating Token Index: 212