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

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

Neuron 1460 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.9362. Min Act: -0.0001

Data Index: 66436 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.9626. Min Act: -0.0001

Data Index: 150047 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8544. Min Act: -0.0001

Data Index: 747877 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.8121. Min Act: -0.0001

Data Index: 1354912 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6313. Min Act: -0.0001

Data Index: 344672 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.7189. Min Act: -0.0001

Data Index: 652025 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6339. Min Act: -0.0001

Data Index: 185186 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6283. Min Act: -0.0001

Data Index: 1106766 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6249. Min Act: -0.0001

Data Index: 335069 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6754. Min Act: -0.0001

Data Index: 341745 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.7144. Min Act: -0.0001

Data Index: 1184133 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.5486. Min Act: -0.0001

Data Index: 595841 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6087. Min Act: -0.0001

Data Index: 351607 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.5804. Min Act: -0.0001

Data Index: 198141 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6192. Min Act: -0.0001

Data Index: 581443 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.4322. Min Act: -0.0001

Data Index: 292681 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.5957. Min Act: -0.0001

Data Index: 505963 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6724. Min Act: -0.0001

Data Index: 917416 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.5502. Min Act: -0.0001

Data Index: 854302 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.9626. Min Range: -1.9626

Max Act: 1.6601. Min Act: -0.0001

Data Index: 941341 (C4 (Web Text))

Max Activating Token Index: 216