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

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

Neuron 2927 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2839. Min Range: -2.2839

Max Act: 2.2839. Min Act: -0.0000

Data Index: 986061 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 2.2839. Min Range: -2.2839

Max Act: 2.0155. Min Act: -0.0000

Data Index: 1053711 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.9580. Min Act: -0.0000

Data Index: 643567 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 2.2839. Min Range: -2.2839

Max Act: 2.0252. Min Act: -0.0000

Data Index: 381940 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.9740. Min Act: -0.0000

Data Index: 387055 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.7806. Min Act: -0.0000

Data Index: 1293387 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.7619. Min Act: -0.0000

Data Index: 682112 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.6383. Min Act: -0.0000

Data Index: 843221 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1319060 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.6353. Min Act: -0.0000

Data Index: 5048 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.6001. Min Act: -0.0000

Data Index: 764304 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.5099. Min Act: -0.0000

Data Index: 636264 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.5753. Min Act: -0.0000

Data Index: 109454 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.5630. Min Act: -0.0000

Data Index: 820838 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.4232. Min Act: -0.0000

Data Index: 343350 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.4009. Min Act: -0.0000

Data Index: 62296 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.5411. Min Act: -0.0000

Data Index: 920386 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.5118. Min Act: -0.0000

Data Index: 683274 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.4892. Min Act: -0.0000

Data Index: 914167 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 2.2839. Min Range: -2.2839

Max Act: 1.5935. Min Act: -0.0000

Data Index: 459493 (C4 (Web Text))

Max Activating Token Index: 653