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

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

Neuron 4240 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1078024 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.8236. Min Act: -0.0000

Data Index: 32753 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.8063. Min Act: -0.0000

Data Index: 314434 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.6952. Min Act: -0.0000

Data Index: 160932 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.7624. Min Act: -0.0000

Data Index: 526301 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.7685. Min Act: -0.0000

Data Index: 1164940 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.8042. Min Act: -0.0000

Data Index: 488521 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1094463 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.6712. Min Act: -0.0000

Data Index: 272016 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.7464. Min Act: -0.0000

Data Index: 463542 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.6415. Min Act: -0.0000

Data Index: 873054 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.6510. Min Act: -0.0000

Data Index: 917995 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.5605. Min Act: -0.0000

Data Index: 332662 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.5578. Min Act: -0.0000

Data Index: 1161213 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.5329. Min Act: -0.0000

Data Index: 658339 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.5321. Min Act: -0.0000

Data Index: 791765 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.4223. Min Act: -0.0000

Data Index: 894027 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.4239. Min Act: -0.0000

Data Index: 221306 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.4284. Min Act: -0.0000

Data Index: 704744 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 1.9999. Min Range: -1.9999

Max Act: 1.5849. Min Act: -0.0000

Data Index: 708970 (C4 (Web Text))

Max Activating Token Index: 894