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

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

Neuron 2829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0062. Min Act: -0.0002

Data Index: 577998 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1587118 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1367212 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0051. Min Act: -0.0002

Data Index: 550112 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0044. Min Act: -0.0002

Data Index: 1445290 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1583545 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0042. Min Act: -0.0002

Data Index: 18866 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1566027 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0029. Min Act: -0.0002

Data Index: 432537 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0039. Min Act: -0.0002

Data Index: 658263 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1147086 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1155666 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0036. Min Act: -0.0002

Data Index: 627520 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0036. Min Act: -0.0002

Data Index: 275084 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0035. Min Act: -0.0002

Data Index: 730620 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1426817 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0036. Min Act: -0.0002

Data Index: 980987 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0033. Min Act: -0.0002

Data Index: 1411168 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0035. Min Act: -0.0002

Data Index: 939858 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1603092 (Python Code)

Max Activating Token Index: 152