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

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

Neuron 802 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1643418 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7803. Min Act: -0.0000

Data Index: 686149 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7077. Min Act: -0.0000

Data Index: 551258 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6716. Min Act: -0.0000

Data Index: 455203 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6689. Min Act: -0.0000

Data Index: 561996 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6475. Min Act: -0.0000

Data Index: 127163 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5889. Min Act: -0.0000

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1485815 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5803. Min Act: -0.0000

Data Index: 270435 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6342. Min Act: -0.0000

Data Index: 786961 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1005203 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1114329 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5611. Min Act: -0.0000

Data Index: 646933 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1443351 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5539. Min Act: -0.0000

Data Index: 441929 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1060380 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1134191 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1458179 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5410. Min Act: -0.0000

Data Index: 532418 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.5471. Min Act: -0.0000

Data Index: 394504 (C4 (Web Text))

Max Activating Token Index: 714