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

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

Neuron 6075 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: 0.2803. Min Range: -0.2803

Max Act: 0.2654. Min Act: -0.0000

Data Index: 176400 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2803. Min Act: -0.0000

Data Index: 227122 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2401. Min Act: -0.0000

Data Index: 824720 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2317. Min Act: -0.0000

Data Index: 626619 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2109. Min Act: -0.0000

Data Index: 325589 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2316. Min Act: -0.0000

Data Index: 170476 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1084008 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1094146 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1111391 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2001. Min Act: -0.0000

Data Index: 699845 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1976. Min Act: -0.0000

Data Index: 520569 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1982. Min Act: -0.0000

Data Index: 14515 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1847. Min Act: -0.0000

Data Index: 505609 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1853. Min Act: -0.0000

Data Index: 153941 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1829. Min Act: -0.0000

Data Index: 218024 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1805. Min Act: -0.0000

Data Index: 275165 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1806. Min Act: -0.0000

Data Index: 90709 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1819. Min Act: -0.0000

Data Index: 850276 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1935. Min Act: -0.0000

Data Index: 501240 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1778. Min Act: -0.0000

Data Index: 391687 (C4 (Web Text))

Max Activating Token Index: 191