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

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

Neuron 1238 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1016514 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2503. Min Act: -0.0001

Data Index: 487456 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2251. Min Act: -0.0002

Data Index: 494055 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2222. Min Act: -0.0002

Data Index: 290695 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2240. Min Act: -0.0002

Data Index: 1357099 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2451. Min Act: -0.0002

Data Index: 803653 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2174. Min Act: -0.0001

Data Index: 414900 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1813. Min Act: -0.0002

Data Index: 560038 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1914. Min Act: -0.0002

Data Index: 501441 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1872. Min Act: -0.0001

Data Index: 725683 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2062. Min Act: -0.0002

Data Index: 756512 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1892. Min Act: -0.0002

Data Index: 157074 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2157. Min Act: -0.0001

Data Index: 654136 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2009. Min Act: -0.0001

Data Index: 183914 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2158. Min Act: -0.0002

Data Index: 553869 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1994. Min Act: -0.0001

Data Index: 1179661 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1967. Min Act: -0.0001

Data Index: 57653 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1353173 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1893. Min Act: -0.0001

Data Index: 121125 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1895. Min Act: -0.0002

Data Index: 1322934 (C4 (Web Text))

Max Activating Token Index: 51