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

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

Neuron 4064 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: 2.9580. Min Range: -2.9580

Max Act: 2.9580. Min Act: -0.0000

Data Index: 1308251 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 2.9580. Min Range: -2.9580

Max Act: 2.0069. Min Act: -0.0000

Data Index: 1292542 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.8471. Min Act: -0.0000

Data Index: 180958 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.8614. Min Act: -0.0000

Data Index: 544797 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.8048. Min Act: -0.0000

Data Index: 349595 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.6490. Min Act: -0.0000

Data Index: 183564 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.8352. Min Act: -0.0000

Data Index: 363633 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.7158. Min Act: -0.0000

Data Index: 13311 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1347251 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.6031. Min Act: -0.0000

Data Index: 574606 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.6856. Min Act: -0.0000

Data Index: 861903 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1116280 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.6073. Min Act: -0.0000

Data Index: 696395 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1274721 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1332518 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.5483. Min Act: -0.0000

Data Index: 170102 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.5331. Min Act: -0.0000

Data Index: 757486 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.4561. Min Act: -0.0000

Data Index: 238011 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.5232. Min Act: -0.0000

Data Index: 739555 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 2.9580. Min Range: -2.9580

Max Act: 1.5093. Min Act: -0.0000

Data Index: 23946 (C4 (Web Text))

Max Activating Token Index: 798