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

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

Neuron 4689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.9870. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7340. Min Act: -0.0000

Data Index: 516246 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1239190 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6683. Min Act: -0.0000

Data Index: 163772 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6732. Min Act: -0.0000

Data Index: 775468 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6174. Min Act: -0.0000

Data Index: 250075 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6579. Min Act: -0.0000

Data Index: 346756 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6501. Min Act: -0.0000

Data Index: 35265 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5924. Min Act: -0.0000

Data Index: 1038186 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1139767 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1351183 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5893. Min Act: -0.0000

Data Index: 840734 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1358958 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5574. Min Act: -0.0000

Data Index: 698612 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5599. Min Act: -0.0000

Data Index: 652541 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6169. Min Act: -0.0000

Data Index: 805507 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5429. Min Act: -0.0000

Data Index: 100424 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.5216. Min Act: -0.0000

Data Index: 220732 (C4 (Web Text))

Max Activating Token Index: 895