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

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

Neuron 4348 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4194. Min Range: -2.4194

Max Act: 2.4194. Min Act: -0.0000

Data Index: 934304 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 2.4194. Min Range: -2.4194

Max Act: 2.1909. Min Act: -0.0000

Data Index: 1003472 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.9866. Min Act: -0.0000

Data Index: 1165740 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 2.4194. Min Range: -2.4194

Max Act: 2.2128. Min Act: -0.0000

Data Index: 91286 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 2.4194. Min Range: -2.4194

Max Act: 2.1313. Min Act: -0.0000

Data Index: 936678 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.9378. Min Act: -0.0000

Data Index: 220955 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.8846. Min Act: -0.0000

Data Index: 932484 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.7889. Min Act: -0.0000

Data Index: 557866 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.8517. Min Act: -0.0000

Data Index: 578090 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.8375. Min Act: -0.0000

Data Index: 665483 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.7906. Min Act: -0.0000

Data Index: 782537 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.6193. Min Act: -0.0000

Data Index: 811453 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.5837. Min Act: -0.0000

Data Index: 857488 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.6809. Min Act: -0.0000

Data Index: 273814 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.8504. Min Act: -0.0000

Data Index: 370362 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1098480 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.7201. Min Act: -0.0000

Data Index: 257820 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.6127. Min Act: -0.0000

Data Index: 392107 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.5898. Min Act: -0.0000

Data Index: 525227 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 2.4194. Min Range: -2.4194

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1011146 (C4 (Web Text))

Max Activating Token Index: 194