Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.3692. Min Act: -0.0000

Data Index: 228680 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.4194. Min Act: 0.0000

Data Index: 517187 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2953. Min Act: -0.0000

Data Index: 1308435 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2260. Min Act: -0.0000

Data Index: 88252 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2672. Min Act: -0.0001

Data Index: 515530 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1888. Min Act: 0.0000

Data Index: 654707 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2261. Min Act: 0.0000

Data Index: 1358239 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1849. Min Act: 0.0000

Data Index: 497584 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1320530 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0936. Min Act: -0.0000

Data Index: 917574 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0495. Min Act: -0.0000

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1235865 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0265. Min Act: -0.0000

Data Index: 782479 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0489. Min Act: -0.0001

Data Index: 880252 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0455. Min Act: -0.0000

Data Index: 88632 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0435. Min Act: -0.0000

Data Index: 994612 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0048. Min Act: -0.0000

Data Index: 289990 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.4194. Min Range: -1.4194

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1069239 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0805. Min Act: -0.0000

Data Index: 788933 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.4194. Min Range: -1.4194

Max Act: 1.0321. Min Act: -0.0000

Data Index: 522159 (C4 (Web Text))

Max Activating Token Index: 89