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

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

Neuron 1330 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: 3.9378. Min Range: -3.9378

Max Act: 3.9378. Min Act: -0.0000

Data Index: 1196801 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.5810. Min Act: -0.0000

Data Index: 1038447 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.6270. Min Act: -0.0000

Data Index: 545427 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.9278. Min Act: -0.0000

Data Index: 179417 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.7237. Min Act: -0.0000

Data Index: 916945 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.5034. Min Act: -0.0000

Data Index: 194718 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4623. Min Act: -0.0000

Data Index: 495285 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.6304. Min Act: -0.0000

Data Index: 115584 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4539. Min Act: -0.0000

Data Index: 83141 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.2998. Min Act: -0.0000

Data Index: 233443 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.7366. Min Act: -0.0000

Data Index: 1232916 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4128. Min Act: -0.0000

Data Index: 872888 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.7207. Min Act: -0.0000

Data Index: 599708 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.3591. Min Act: -0.0000

Data Index: 64702 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4919. Min Act: -0.0000

Data Index: 531822 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.3441. Min Act: -0.0000

Data Index: 453902 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.3514. Min Act: -0.0000

Data Index: 494265 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4542. Min Act: -0.0000

Data Index: 301182 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.3315. Min Act: -0.0000

Data Index: 1256668 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.9378. Min Range: -3.9378

Max Act: 3.4200. Min Act: -0.0000

Data Index: 474475 (C4 (Web Text))

Max Activating Token Index: 565