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

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

Neuron 3495 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: 0.1295. Min Range: -0.1295

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1420662 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1618929 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0918. Min Act: -0.0001

Data Index: 536177 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1492461 (Python Code)

Max Activating Token Index: 514

Text #4

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0891. Min Act: -0.0001

Data Index: 13327 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0923. Min Act: -0.0001

Data Index: 972289 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0895. Min Act: -0.0001

Data Index: 771861 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1537122 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0973. Min Act: -0.0001

Data Index: 731456 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1654033 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1171024 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0893. Min Act: -0.0001

Data Index: 990564 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0897. Min Act: -0.0001

Data Index: 659203 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0856. Min Act: -0.0001

Data Index: 265208 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1289998 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1339097 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1554396 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0842. Min Act: -0.0001

Data Index: 982529 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1189864 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0908. Min Act: -0.0001

Data Index: 106210 (C4 (Web Text))

Max Activating Token Index: 21