Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 85 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1210. Min Act: -0.0003

Data Index: 1631728 (Python Code)

Max Activating Token Index: 229

Text #1

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1464375 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1049. Min Act: -0.0003

Data Index: 1397046 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0939. Min Act: -0.0003

Data Index: 1549618 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0911. Min Act: -0.0003

Data Index: 1433997 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0886. Min Act: -0.0003

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0823. Min Act: -0.0003

Data Index: 415971 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0869. Min Act: -0.0003

Data Index: 110620 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1409217 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0858. Min Act: -0.0004

Data Index: 1563298 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0859. Min Act: -0.0003

Data Index: 523393 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0829. Min Act: -0.0003

Data Index: 253502 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0834. Min Act: -0.0003

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0823. Min Act: -0.0003

Data Index: 656649 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0823. Min Act: -0.0004

Data Index: 1654599 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0831. Min Act: -0.0003

Data Index: 862788 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0830. Min Act: -0.0003

Data Index: 1420755 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0788. Min Act: -0.0003

Data Index: 693509 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1515984 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0806. Min Act: -0.0003

Data Index: 336431 (C4 (Web Text))

Max Activating Token Index: 344