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

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

Neuron 2193 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0001

Data Index: 748027 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0941. Min Act: -0.0001

Data Index: 170161 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1603425 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1236970 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0817. Min Act: -0.0001

Data Index: 622940 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0802. Min Act: -0.0001

Data Index: 378656 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1396507 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1094084 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0768. Min Act: -0.0001

Data Index: 96881 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0760. Min Act: -0.0001

Data Index: 88797 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1703 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1059784 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1490331 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0679. Min Act: -0.0001

Data Index: 594946 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1155090 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0675. Min Act: -0.0001

Data Index: 881218 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0672. Min Act: -0.0001

Data Index: 950226 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1338216 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0661. Min Act: -0.0001

Data Index: 880103 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0670. Min Act: -0.0001

Data Index: 942267 (C4 (Web Text))

Max Activating Token Index: 102