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

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

Neuron 4397 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1253. Min Act: -0.0002

Data Index: 471251 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1545377 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1404431 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1605592 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0900. Min Act: -0.0002

Data Index: 393585 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0870. Min Act: -0.0002

Data Index: 257062 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0843. Min Act: -0.0002

Data Index: 956816 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1623459 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1556351 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0804. Min Act: -0.0002

Data Index: 166039 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0803. Min Act: -0.0002

Data Index: 263578 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0768. Min Act: -0.0002

Data Index: 28257 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0770. Min Act: -0.0002

Data Index: 889320 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1587284 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0753. Min Act: -0.0002

Data Index: 201153 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1083245 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1598554 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1401733 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1539277 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.1253. Min Range: -0.1253

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1388000 (Python Code)

Max Activating Token Index: 805