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

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

Neuron 4573 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.7508. Min Act: -0.0000

Data Index: 357929 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6895. Min Act: -0.0000

Data Index: 265414 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.7132. Min Act: -0.0000

Data Index: 840641 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6585. Min Act: 0.0000

Data Index: 528771 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6009. Min Act: -0.0000

Data Index: 680510 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1080850 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.6011. Min Act: -0.0000

Data Index: 166856 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1128811 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5843. Min Act: -0.0000

Data Index: 90795 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5498. Min Act: -0.0000

Data Index: 307414 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5794. Min Act: -0.0000

Data Index: 727103 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5419. Min Act: -0.0000

Data Index: 188880 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5295. Min Act: -0.0000

Data Index: 111431 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5213. Min Act: -0.0000

Data Index: 646474 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1158959 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1174362 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1272315 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4843. Min Act: -0.0000

Data Index: 920025 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4683. Min Act: -0.0000

Data Index: 603984 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.7508. Min Range: -0.7508

Max Act: 0.4803. Min Act: -0.0000

Data Index: 468977 (C4 (Web Text))

Max Activating Token Index: 576