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

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

Neuron 2491 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: 1.3795. Min Range: -1.3795

Max Act: 1.3795. Min Act: -0.0001

Data Index: 1369954 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.2395. Min Act: -0.0001

Data Index: 1514126 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.2251. Min Act: -0.0001

Data Index: 279868 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.1317. Min Act: -0.0001

Data Index: 874227 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0033. Min Act: -0.0001

Data Index: 480787 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0334. Min Act: -0.0001

Data Index: 262718 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0888. Min Act: -0.0001

Data Index: 1622209 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9790. Min Act: -0.0001

Data Index: 735073 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0560. Min Act: -0.0001

Data Index: 902960 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1243984 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0181. Min Act: -0.0001

Data Index: 427245 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9209. Min Act: -0.0001

Data Index: 442578 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.8935. Min Act: -0.0001

Data Index: 890762 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.3795. Min Range: -1.3795

Max Act: 1.0253. Min Act: -0.0001

Data Index: 1585552 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9193. Min Act: -0.0001

Data Index: 1518373 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9602. Min Act: -0.0001

Data Index: 557407 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1183913 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9660. Min Act: -0.0001

Data Index: 1656201 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9685. Min Act: -0.0001

Data Index: 576824 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.3795. Min Range: -1.3795

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1374308 (Python Code)

Max Activating Token Index: 672