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

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

Neuron 2587 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3737. Min Act: -0.0000

Data Index: 914676 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3483. Min Act: -0.0000

Data Index: 59357 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1413211 (Python Code)

Max Activating Token Index: 182

Text #3

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1231922 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1117003 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3178. Min Act: -0.0000

Data Index: 583537 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3184. Min Act: -0.0000

Data Index: 145543 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1131578 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3222. Min Act: -0.0000

Data Index: 642064 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3260. Min Act: -0.0000

Data Index: 178109 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3239. Min Act: -0.0000

Data Index: 588236 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1077555 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3018. Min Act: -0.0000

Data Index: 669210 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1646984 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2952. Min Act: -0.0000

Data Index: 96632 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3121. Min Act: -0.0000

Data Index: 98823 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2994. Min Act: -0.0000

Data Index: 272527 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1627948 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3036. Min Act: -0.0000

Data Index: 430963 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1281387 (C4 (Web Text))

Max Activating Token Index: 472