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

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

Neuron 1410 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: 0.7338. Min Range: -0.7338

Max Act: 0.7338. Min Act: -0.0002

Data Index: 1162977 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6853. Min Act: -0.0002

Data Index: 580080 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6677. Min Act: -0.0002

Data Index: 718679 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6300. Min Act: -0.0002

Data Index: 370017 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6087. Min Act: -0.0002

Data Index: 544475 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6373. Min Act: -0.0002

Data Index: 1138575 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6080. Min Act: -0.0002

Data Index: 449715 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6167. Min Act: -0.0002

Data Index: 1253037 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6204. Min Act: -0.0002

Data Index: 1161645 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6334. Min Act: -0.0002

Data Index: 1167144 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6061. Min Act: -0.0002

Data Index: 125281 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5881. Min Act: -0.0002

Data Index: 1357713 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6237. Min Act: -0.0002

Data Index: 197602 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5667. Min Act: -0.0002

Data Index: 922564 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5806. Min Act: -0.0002

Data Index: 1179742 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5715. Min Act: -0.0002

Data Index: 633440 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5734. Min Act: -0.0002

Data Index: 491305 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6069. Min Act: -0.0002

Data Index: 810916 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6038. Min Act: -0.0002

Data Index: 92000 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5827. Min Act: -0.0002

Data Index: 552802 (C4 (Web Text))

Max Activating Token Index: 147