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

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

Neuron 4702 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.6710. Min Act: -0.0000

Data Index: 78026 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1172684 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5396. Min Act: -0.0000

Data Index: 693101 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5299. Min Act: -0.0000

Data Index: 853046 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5202. Min Act: -0.0000

Data Index: 163960 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5138. Min Act: -0.0000

Data Index: 691153 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4735. Min Act: -0.0000

Data Index: 55846 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5091. Min Act: -0.0000

Data Index: 253992 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1309117 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1020736 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4482. Min Act: -0.0000

Data Index: 306496 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4296. Min Act: -0.0000

Data Index: 841762 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1182435 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4224. Min Act: -0.0000

Data Index: 989920 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4179. Min Act: 0.0001

Data Index: 467845 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4335. Min Act: -0.0000

Data Index: 647648 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1329902 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1097406 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1225987 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.6710. Min Range: -0.6710

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1009164 (C4 (Web Text))

Max Activating Token Index: 663