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

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

Neuron 2164 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: 2.0113. Min Range: -2.0113

Max Act: 2.0113. Min Act: -0.0000

Data Index: 261931 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.9082. Min Act: -0.0000

Data Index: 271012 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.8825. Min Act: -0.0001

Data Index: 172943 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.8158. Min Act: -0.0000

Data Index: 599859 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.8059. Min Act: -0.0000

Data Index: 865127 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.7255. Min Act: -0.0000

Data Index: 949207 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5823. Min Act: -0.0000

Data Index: 269302 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5855. Min Act: -0.0000

Data Index: 598235 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.6011. Min Act: -0.0000

Data Index: 299565 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5666. Min Act: -0.0000

Data Index: 530218 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.3673. Min Act: -0.0000

Data Index: 38210 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.4545. Min Act: -0.0000

Data Index: 385164 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5301. Min Act: -0.0000

Data Index: 647033 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5376. Min Act: -0.0000

Data Index: 892037 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1156165 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.6557. Min Act: -0.0001

Data Index: 487108 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.4657. Min Act: -0.0000

Data Index: 829835 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.4087. Min Act: -0.0000

Data Index: 565357 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.5242. Min Act: -0.0000

Data Index: 724725 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 2.0113. Min Range: -2.0113

Max Act: 1.4180. Min Act: -0.0000

Data Index: 375660 (C4 (Web Text))

Max Activating Token Index: 667