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

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

Neuron 2634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.3035. Min Act: -0.0001

Data Index: 458885 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2907. Min Act: -0.0001

Data Index: 824496 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1308374 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2598. Min Act: -0.0001

Data Index: 397597 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1312026 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2488. Min Act: -0.0001

Data Index: 152372 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2964. Min Act: -0.0001

Data Index: 1346165 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2855. Min Act: -0.0001

Data Index: 357546 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2507. Min Act: -0.0001

Data Index: 206882 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2883. Min Act: -0.0001

Data Index: 1023659 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2321. Min Act: -0.0001

Data Index: 49901 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2529. Min Act: -0.0001

Data Index: 21868 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2421. Min Act: -0.0001

Data Index: 1107304 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2285. Min Act: -0.0001

Data Index: 804659 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2281. Min Act: -0.0001

Data Index: 730377 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2255. Min Act: -0.0001

Data Index: 273007 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2349. Min Act: -0.0001

Data Index: 180717 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2581. Min Act: -0.0001

Data Index: 18408 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2311. Min Act: -0.0001

Data Index: 312886 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2327. Min Act: -0.0001

Data Index: 1277427 (C4 (Web Text))

Max Activating Token Index: 736