Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1277338 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.8265. Min Act: -0.0000

Data Index: 807797 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.6099. Min Act: -0.0000

Data Index: 73774 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.4805. Min Act: -0.0000

Data Index: 444364 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.6765. Min Act: -0.0000

Data Index: 1075839 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.5899. Min Act: -0.0000

Data Index: 499873 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.5398. Min Act: -0.0000

Data Index: 62952 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.5898. Min Act: -0.0000

Data Index: 1173229 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.5440. Min Act: -0.0000

Data Index: 89644 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.4336. Min Act: -0.0000

Data Index: 504588 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3584. Min Act: -0.0000

Data Index: 634969 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1300066 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3123. Min Act: -0.0000

Data Index: 11386 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3999. Min Act: -0.0000

Data Index: 314570 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1357730 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.2896. Min Act: -0.0000

Data Index: 291669 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3527. Min Act: -0.0000

Data Index: 173789 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1140923 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.9101. Min Range: -1.9101

Max Act: 1.3050. Min Act: -0.0000

Data Index: 208775 (C4 (Web Text))

Max Activating Token Index: 300