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

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

Neuron 38 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.6672. Min Act: -0.0000

Data Index: 472187 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5633. Min Act: -0.0000

Data Index: 221313 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1370628 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5891. Min Act: 0.0000

Data Index: 123069 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5466. Min Act: -0.0000

Data Index: 769057 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1281795 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5078. Min Act: -0.0000

Data Index: 754098 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5048. Min Act: -0.0000

Data Index: 998528 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1191037 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1038966 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4814. Min Act: -0.0000

Data Index: 385377 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1521984 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1116680 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1213389 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1336007 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4524. Min Act: -0.0000

Data Index: 852706 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4806. Min Act: -0.0000

Data Index: 10684 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1045443 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4586. Min Act: -0.0000

Data Index: 1263903 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.6672. Min Range: -0.6672

Max Act: 0.4552. Min Act: -0.0000

Data Index: 153756 (C4 (Web Text))

Max Activating Token Index: 92