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

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

Neuron 2540 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: 0.8977. Min Range: -0.8977

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1115215 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8977. Min Act: -0.0000

Data Index: 150797 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8719. Min Act: -0.0000

Data Index: 537563 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1358362 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7675. Min Act: -0.0000

Data Index: 756575 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7625. Min Act: -0.0000

Data Index: 41160 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.7515. Min Act: -0.0000

Data Index: 927710 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6297. Min Act: -0.0000

Data Index: 339608 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1048170 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1147838 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6039. Min Act: -0.0000

Data Index: 469250 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6174. Min Act: -0.0000

Data Index: 211479 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6139. Min Act: -0.0000

Data Index: 449122 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6086. Min Act: -0.0000

Data Index: 515473 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6277. Min Act: -0.0000

Data Index: 564973 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6064. Min Act: -0.0000

Data Index: 886058 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.6367. Min Act: -0.0001

Data Index: 799392 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.5994. Min Act: -0.0000

Data Index: 790712 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.5816. Min Act: -0.0000

Data Index: 272057 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.8977. Min Range: -0.8977

Max Act: 0.5801. Min Act: -0.0000

Data Index: 782235 (C4 (Web Text))

Max Activating Token Index: 497