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

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

Neuron 868 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4308. Min Act: -0.0002

Data Index: 176689 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3403. Min Act: -0.0002

Data Index: 641521 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3182. Min Act: -0.0002

Data Index: 343667 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3302. Min Act: -0.0002

Data Index: 977370 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2959. Min Act: -0.0002

Data Index: 24077 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3157. Min Act: -0.0002

Data Index: 785384 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2896. Min Act: -0.0002

Data Index: 580474 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3030. Min Act: -0.0002

Data Index: 1307272 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2942. Min Act: -0.0002

Data Index: 474990 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3288. Min Act: -0.0002

Data Index: 581640 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3176. Min Act: -0.0003

Data Index: 582424 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2879. Min Act: -0.0002

Data Index: 162810 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3122. Min Act: -0.0002

Data Index: 1173124 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3060. Min Act: -0.0002

Data Index: 1124018 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3007. Min Act: -0.0002

Data Index: 176737 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3055. Min Act: -0.0002

Data Index: 44370 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2889. Min Act: -0.0003

Data Index: 810076 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2920. Min Act: -0.0002

Data Index: 923882 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3080. Min Act: -0.0002

Data Index: 460258 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3085. Min Act: -0.0002

Data Index: 338528 (C4 (Web Text))

Max Activating Token Index: 578