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

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

Neuron 1758 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1597978 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1210263 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5368. Min Act: -0.0000

Data Index: 157035 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1639301 (Python Code)

Max Activating Token Index: 164

Text #4

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5660. Min Act: -0.0000

Data Index: 698826 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5006. Min Act: -0.0000

Data Index: 384332 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5140. Min Act: -0.0000

Data Index: 930587 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4961. Min Act: -0.0000

Data Index: 606865 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5315. Min Act: -0.0000

Data Index: 808680 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4934. Min Act: -0.0000

Data Index: 799805 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1496314 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.5024. Min Act: -0.0000

Data Index: 174205 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4952. Min Act: -0.0000

Data Index: 505275 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1573510 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4874. Min Act: -0.0000

Data Index: 44145 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4627. Min Act: -0.0000

Data Index: 144669 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4727. Min Act: -0.0000

Data Index: 176334 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1514009 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4663. Min Act: -0.0000

Data Index: 981293 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.9826. Min Range: -0.9826

Max Act: 0.4777. Min Act: -0.0000

Data Index: 550148 (C4 (Web Text))

Max Activating Token Index: 867