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

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

Neuron 4060 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2269. Min Range: -6.2269

Max Act: 6.2269. Min Act: -0.0000

Data Index: 708203 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.9804. Min Act: -0.0000

Data Index: 1292578 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.3155. Min Act: -0.0000

Data Index: 1119091 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.2101. Min Act: -0.0000

Data Index: 857986 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.1764. Min Act: -0.0000

Data Index: 529668 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.1151. Min Act: -0.0000

Data Index: 43179 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.9294. Min Act: -0.0000

Data Index: 926194 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.8195. Min Act: -0.0000

Data Index: 90095 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.5433. Min Act: -0.0000

Data Index: 1179026 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.4284. Min Act: -0.0000

Data Index: 838609 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.6099. Min Act: -0.0000

Data Index: 230860 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.7665. Min Act: -0.0000

Data Index: 361094 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.9919. Min Act: 0.0000

Data Index: 256119 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.6351. Min Act: -0.0000

Data Index: 49939 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 6.2269. Min Range: -6.2269

Max Act: 5.1083. Min Act: -0.0000

Data Index: 500616 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.4208. Min Act: -0.0000

Data Index: 1310055 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.3510. Min Act: -0.0000

Data Index: 341685 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.3879. Min Act: -0.0000

Data Index: 34305 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.3028. Min Act: -0.0000

Data Index: 405778 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 6.2269. Min Range: -6.2269

Max Act: 4.4390. Min Act: -0.0000

Data Index: 251531 (C4 (Web Text))

Max Activating Token Index: 331