Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1026 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2314. Min Act: -0.0001

Data Index: 808571 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2106. Min Act: -0.0002

Data Index: 1288448 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2272. Min Act: -0.0002

Data Index: 301092 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1354223 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1884. Min Act: -0.0002

Data Index: 995489 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1866. Min Act: -0.0002

Data Index: 521201 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1880. Min Act: -0.0002

Data Index: 126088 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.2030. Min Act: -0.0002

Data Index: 752085 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1818. Min Act: -0.0002

Data Index: 1340970 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1758. Min Act: -0.0002

Data Index: 750599 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1818. Min Act: -0.0001

Data Index: 132608 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1866. Min Act: -0.0002

Data Index: 1207519 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1979. Min Act: -0.0002

Data Index: 123361 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1841. Min Act: -0.0001

Data Index: 636078 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1634. Min Act: -0.0002

Data Index: 252815 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1847. Min Act: -0.0002

Data Index: 1063876 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1861. Min Act: -0.0001

Data Index: 421215 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1662. Min Act: -0.0002

Data Index: 476254 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1789. Min Act: -0.0002

Data Index: 868084 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.2314. Min Range: -0.2314

Max Act: 0.1906. Min Act: -0.0002

Data Index: 563277 (C4 (Web Text))

Max Activating Token Index: 478