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

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

Neuron 3267 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1015476 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1229223 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1098181 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0002

Data Index: 533128 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1169302 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0096. Min Act: -0.0002

Data Index: 631699 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0002

Data Index: 710980 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0093. Min Act: -0.0002

Data Index: 434961 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1055358 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 138885 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 155618 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 842131 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 997926 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1017869 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0002

Data Index: 302950 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1253683 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0002

Data Index: 421378 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0089. Min Act: -0.0002

Data Index: 541342 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0090. Min Act: -0.0002

Data Index: 231455 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0088. Min Act: -0.0002

Data Index: 780145 (C4 (Web Text))

Max Activating Token Index: 507