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

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

Neuron 1271 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8818. Min Act: -0.0002

Data Index: 357623 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9837. Min Act: -0.0001

Data Index: 887892 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9070. Min Act: -0.0001

Data Index: 773740 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1031664 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9345. Min Act: -0.0001

Data Index: 745921 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8359. Min Act: -0.0001

Data Index: 1025381 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.0602. Min Range: -1.0602

Max Act: 1.0602. Min Act: -0.0001

Data Index: 1328471 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8735. Min Act: -0.0001

Data Index: 659585 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8468. Min Act: -0.0001

Data Index: 892819 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7856. Min Act: -0.0001

Data Index: 255257 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8695. Min Act: -0.0001

Data Index: 396906 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8293. Min Act: -0.0001

Data Index: 517254 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1189382 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7968. Min Act: -0.0001

Data Index: 1147129 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8882. Min Act: -0.0001

Data Index: 566447 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8338. Min Act: -0.0001

Data Index: 1164127 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7903. Min Act: -0.0001

Data Index: 579147 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7914. Min Act: -0.0001

Data Index: 457180 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6732. Min Act: -0.0001

Data Index: 1075290 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7845. Min Act: -0.0001

Data Index: 572190 (C4 (Web Text))

Max Activating Token Index: 573