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

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

Neuron 4912 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.7108. Min Act: -0.0000

Data Index: 906455 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6192. Min Act: -0.0000

Data Index: 281619 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6193. Min Act: -0.0000

Data Index: 3047 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6165. Min Act: -0.0000

Data Index: 700232 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6113. Min Act: -0.0000

Data Index: 460740 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6101. Min Act: -0.0000

Data Index: 702113 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1316065 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5932. Min Act: -0.0000

Data Index: 84324 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5771. Min Act: -0.0000

Data Index: 36389 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5501. Min Act: -0.0000

Data Index: 518645 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.6209. Min Act: -0.0000

Data Index: 897915 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5931. Min Act: -0.0000

Data Index: 248276 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1465474 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1334648 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1019047 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1032960 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5287. Min Act: -0.0000

Data Index: 807206 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5411. Min Act: -0.0000

Data Index: 70282 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5378. Min Act: -0.0000

Data Index: 749006 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.7108. Min Range: -0.7108

Max Act: 0.5490. Min Act: -0.0000

Data Index: 758073 (C4 (Web Text))

Max Activating Token Index: 12