Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5891 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.7964. Min Act: -0.0000

Data Index: 1025004 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.8592. Min Act: -0.0000

Data Index: 755294 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.2995. Min Act: -0.0000

Data Index: 1059935 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.3254. Min Act: -0.0000

Data Index: 404287 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.2680. Min Act: -0.0000

Data Index: 157991 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.9393. Min Act: -0.0000

Data Index: 432296 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1312100 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.0529. Min Act: -0.0000

Data Index: 874854 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.0074. Min Act: -0.0000

Data Index: 217904 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.8755. Min Act: -0.0000

Data Index: 467136 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.8484. Min Act: -0.0000

Data Index: 658659 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.9548. Min Act: -0.0000

Data Index: 536339 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.9350. Min Act: -0.0000

Data Index: 241906 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.8310. Min Act: -0.0000

Data Index: 210854 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.9218. Min Act: -0.0000

Data Index: 1280452 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.9258. Min Act: -0.0000

Data Index: 908290 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 2.8592. Min Range: -2.8592

Max Act: 2.0238. Min Act: -0.0000

Data Index: 752171 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.8143. Min Act: -0.0000

Data Index: 235537 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.9161. Min Act: -0.0000

Data Index: 124841 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.8592. Min Range: -2.8592

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1139820 (C4 (Web Text))

Max Activating Token Index: 75