Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 373 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2826. Min Act: -0.0002

Data Index: 1328261 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2664. Min Act: -0.0001

Data Index: 170518 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2396. Min Act: -0.0002

Data Index: 1053276 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2201. Min Act: -0.0002

Data Index: 414262 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2311. Min Act: -0.0002

Data Index: 761648 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2377. Min Act: -0.0002

Data Index: 1023750 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2293. Min Act: -0.0002

Data Index: 443357 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2346. Min Act: -0.0002

Data Index: 589923 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2286. Min Act: -0.0002

Data Index: 193214 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2282. Min Act: -0.0002

Data Index: 1273115 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2074. Min Act: -0.0002

Data Index: 1008951 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2169. Min Act: -0.0002

Data Index: 584551 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2316. Min Act: -0.0002

Data Index: 1136351 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2158. Min Act: -0.0002

Data Index: 1126629 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2397. Min Act: -0.0002

Data Index: 316530 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2069. Min Act: -0.0002

Data Index: 1341865 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2233. Min Act: -0.0002

Data Index: 1289484 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1739. Min Act: -0.0002

Data Index: 207306 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.1908. Min Act: -0.0001

Data Index: 906081 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.2826. Min Range: -0.2826

Max Act: 0.2149. Min Act: -0.0002

Data Index: 1245349 (C4 (Web Text))

Max Activating Token Index: 487