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

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

Neuron 3043 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: 0.0046. Min Range: -0.0046

Max Act: 0.0046. Min Act: -0.0003

Data Index: 449516 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0041. Min Act: -0.0003

Data Index: 275141 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0040. Min Act: -0.0003

Data Index: 208654 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0035. Min Act: -0.0002

Data Index: 750856 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0033. Min Act: -0.0002

Data Index: 352007 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0033. Min Act: -0.0003

Data Index: 134683 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0029. Min Act: -0.0003

Data Index: 225845 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1642288 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1283604 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0029. Min Act: -0.0003

Data Index: 49115 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1578105 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0029. Min Act: -0.0003

Data Index: 175013 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0027. Min Act: -0.0002

Data Index: 498461 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0027. Min Act: -0.0003

Data Index: 403462 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0027. Min Act: -0.0002

Data Index: 964144 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0026. Min Act: -0.0003

Data Index: 966409 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0026. Min Act: -0.0002

Data Index: 848729 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0026. Min Act: -0.0003

Data Index: 26635 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0026. Min Act: -0.0002

Data Index: 854496 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0046. Min Range: -0.0046

Max Act: 0.0025. Min Act: -0.0003

Data Index: 63577 (C4 (Web Text))

Max Activating Token Index: 383