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

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

Neuron 3730 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.7296. Min Act: -0.0000

Data Index: 371310 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6826. Min Act: -0.0000

Data Index: 940382 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6883. Min Act: -0.0000

Data Index: 715170 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6955. Min Act: -0.0000

Data Index: 480054 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5644. Min Act: -0.0000

Data Index: 661930 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5930. Min Act: -0.0000

Data Index: 856664 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6041. Min Act: -0.0000

Data Index: 864885 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5618. Min Act: -0.0000

Data Index: 275055 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6267. Min Act: -0.0000

Data Index: 854379 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5561. Min Act: -0.0000

Data Index: 803893 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4759. Min Act: -0.0000

Data Index: 963786 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1049077 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1293903 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5479. Min Act: -0.0000

Data Index: 171090 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4612. Min Act: -0.0000

Data Index: 57696 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1222381 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.5106. Min Act: -0.0000

Data Index: 160724 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4651. Min Act: -0.0000

Data Index: 17460 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4873. Min Act: -0.0000

Data Index: 705580 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.7296. Min Range: -0.7296

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1459174 (Python Code)

Max Activating Token Index: 358