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

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

Neuron 2115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.4757. Min Act: -0.0000

Data Index: 1014250 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.3404. Min Act: -0.0000

Data Index: 645827 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.3716. Min Act: -0.0000

Data Index: 1243041 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.1857. Min Act: -0.0000

Data Index: 189068 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.0549. Min Act: -0.0000

Data Index: 902295 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.1280. Min Act: -0.0000

Data Index: 1091886 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.1061. Min Act: -0.0000

Data Index: 882312 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.0674. Min Act: -0.0000

Data Index: 496011 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.0561. Min Act: -0.0000

Data Index: 759316 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.1567. Min Act: -0.0000

Data Index: 339228 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.0330. Min Act: -0.0000

Data Index: 324401 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.9854. Min Act: -0.0000

Data Index: 12175 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.0881. Min Act: -0.0000

Data Index: 160084 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 2.4757. Min Range: -2.4757

Max Act: 2.0610. Min Act: -0.0000

Data Index: 249537 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.9625. Min Act: -0.0000

Data Index: 835692 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.9532. Min Act: -0.0000

Data Index: 401811 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.9182. Min Act: -0.0000

Data Index: 667856 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.9231. Min Act: -0.0000

Data Index: 258292 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.8912. Min Act: -0.0000

Data Index: 238934 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 2.4757. Min Range: -2.4757

Max Act: 1.8747. Min Act: -0.0000

Data Index: 708580 (C4 (Web Text))

Max Activating Token Index: 324