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

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

Neuron 4179 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3355. Min Range: -1.3355

Max Act: 1.3355. Min Act: -0.0000

Data Index: 31957 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 1.3355. Min Range: -1.3355

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1343987 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.3355. Min Range: -1.3355

Max Act: 1.1164. Min Act: -0.0000

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9948. Min Act: -0.0000

Data Index: 903097 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9820. Min Act: -0.0000

Data Index: 556530 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9162. Min Act: -0.0000

Data Index: 179985 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.3355. Min Range: -1.3355

Max Act: 1.0047. Min Act: -0.0000

Data Index: 429429 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9313. Min Act: -0.0000

Data Index: 311585 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9375. Min Act: -0.0000

Data Index: 502052 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1020822 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9368. Min Act: -0.0000

Data Index: 300481 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8916. Min Act: -0.0000

Data Index: 839951 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8548. Min Act: -0.0000

Data Index: 509399 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8524. Min Act: -0.0000

Data Index: 453359 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1246312 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8716. Min Act: -0.0000

Data Index: 780598 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8462. Min Act: -0.0000

Data Index: 305301 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1351265 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1259190 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.3355. Min Range: -1.3355

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1119831 (C4 (Web Text))

Max Activating Token Index: 559