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

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

Neuron 517 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.5865. Min Act: -0.0000

Data Index: 713995 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4250. Min Act: -0.0000

Data Index: 235344 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1106276 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4096. Min Act: -0.0000

Data Index: 308286 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1021955 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4124. Min Act: -0.0000

Data Index: 985557 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1284491 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3861. Min Act: -0.0000

Data Index: 81966 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3992. Min Act: -0.0000

Data Index: 883669 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.2959. Min Act: -0.0000

Data Index: 140906 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3866. Min Act: -0.0000

Data Index: 680893 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1047229 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3863. Min Act: -0.0000

Data Index: 513634 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.4104. Min Act: -0.0000

Data Index: 544485 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1077221 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3676. Min Act: -0.0000

Data Index: 233645 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1601662 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3500. Min Act: -0.0000

Data Index: 115123 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3596. Min Act: -0.0000

Data Index: 578685 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.5865. Min Range: -0.5865

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1171859 (C4 (Web Text))

Max Activating Token Index: 399