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

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

Neuron 2579 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0002

Data Index: 679177 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0130. Min Act: -0.0003

Data Index: 246284 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1569852 (Python Code)

Max Activating Token Index: 122

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0003

Data Index: 862294 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0003

Data Index: 750572 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 920399 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0002

Data Index: 795538 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0003

Data Index: 903503 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0003

Data Index: 678604 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0003

Data Index: 840195 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0002

Data Index: 939982 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0003

Data Index: 561551 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1101036 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1432656 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0003

Data Index: 556637 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0110. Min Act: -0.0003

Data Index: 362648 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0113. Min Act: -0.0003

Data Index: 134502 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0110. Min Act: -0.0002

Data Index: 418882 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0107. Min Act: -0.0003

Data Index: 81329 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0109. Min Act: -0.0003

Data Index: 2706 (C4 (Web Text))

Max Activating Token Index: 367