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

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

Neuron 1636 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: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1507310 (Python Code)

Max Activating Token Index: 250

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1616994 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1474466 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1487996 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1494363 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1656125 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1648349 (Python Code)

Max Activating Token Index: 319

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1416128 (Python Code)

Max Activating Token Index: 306

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1641638 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0047. Min Act: -0.0002

Data Index: 1618178 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0038. Min Act: -0.0002

Data Index: 1406588 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1654236 (Python Code)

Max Activating Token Index: 614

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1592816 (Python Code)

Max Activating Token Index: 126

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0028. Min Act: -0.0003

Data Index: 952204 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1638042 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0027. Min Act: -0.0003

Data Index: 703440 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1457694 (Python Code)

Max Activating Token Index: 728

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1506037 (Python Code)

Max Activating Token Index: 779

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1513826 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0026. Min Act: -0.0002

Data Index: 1406405 (Python Code)

Max Activating Token Index: 284