Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2870 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.4005. Min Act: -0.0003

Data Index: 586003 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.3565. Min Act: -0.0003

Data Index: 1858 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.3129. Min Act: -0.0003

Data Index: 1331949 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2855. Min Act: -0.0003

Data Index: 1091706 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2816. Min Act: -0.0002

Data Index: 474610 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2725. Min Act: -0.0003

Data Index: 949243 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2799. Min Act: -0.0003

Data Index: 749008 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2585. Min Act: -0.0003

Data Index: 516298 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2558. Min Act: -0.0003

Data Index: 1003380 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2467. Min Act: -0.0003

Data Index: 1009966 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2433. Min Act: -0.0003

Data Index: 407661 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2433. Min Act: -0.0003

Data Index: 604564 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2361. Min Act: -0.0002

Data Index: 810157 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2357. Min Act: -0.0003

Data Index: 1222239 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2332. Min Act: -0.0003

Data Index: 939485 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2225. Min Act: -0.0003

Data Index: 854729 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2279. Min Act: -0.0002

Data Index: 408200 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2270. Min Act: -0.0002

Data Index: 196058 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2268. Min Act: -0.0003

Data Index: 478571 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.4005. Min Range: -0.4005

Max Act: 0.2250. Min Act: -0.0003

Data Index: 1057087 (C4 (Web Text))

Max Activating Token Index: 766