Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1578 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6171. Min Act: -0.0003

Data Index: 933567 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6082. Min Act: -0.0003

Data Index: 919630 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6479. Min Act: -0.0003

Data Index: 768225 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6253. Min Act: -0.0003

Data Index: 934112 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5921. Min Act: -0.0003

Data Index: 357766 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5646. Min Act: -0.0003

Data Index: 1201144 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5625. Min Act: -0.0003

Data Index: 526241 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5825. Min Act: -0.0003

Data Index: 848975 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5526. Min Act: -0.0003

Data Index: 315507 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6077. Min Act: -0.0003

Data Index: 1008339 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5255. Min Act: -0.0003

Data Index: 524503 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5883. Min Act: -0.0003

Data Index: 1312265 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.6030. Min Act: -0.0003

Data Index: 617895 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5449. Min Act: -0.0003

Data Index: 54990 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5715. Min Act: -0.0003

Data Index: 342749 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5465. Min Act: -0.0003

Data Index: 453242 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5626. Min Act: -0.0003

Data Index: 992589 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5678. Min Act: -0.0003

Data Index: 1192189 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5240. Min Act: -0.0003

Data Index: 749412 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.6479. Min Range: -0.6479

Max Act: 0.5635. Min Act: -0.0003

Data Index: 650391 (C4 (Web Text))

Max Activating Token Index: 702