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

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

Neuron 4885 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2536. Min Act: -0.0000

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1056779 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2348. Min Act: -0.0000

Data Index: 815334 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2249. Min Act: -0.0000

Data Index: 221072 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2102. Min Act: -0.0000

Data Index: 133251 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2125. Min Act: -0.0000

Data Index: 867098 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2103. Min Act: -0.0000

Data Index: 559012 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2081. Min Act: -0.0000

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2092. Min Act: -0.0000

Data Index: 780095 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1990. Min Act: -0.0000

Data Index: 306885 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2054. Min Act: -0.0000

Data Index: 62793 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1900. Min Act: -0.0000

Data Index: 397482 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2024. Min Act: -0.0000

Data Index: 847604 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1749. Min Act: -0.0000

Data Index: 135277 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1165556 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1908. Min Act: -0.0000

Data Index: 209990 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1889. Min Act: -0.0000

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1150062 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1804. Min Act: -0.0000

Data Index: 123083 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.2536. Min Range: -0.2536

Max Act: 0.1908. Min Act: -0.0000

Data Index: 932451 (C4 (Web Text))

Max Activating Token Index: 1006