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

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

Neuron 4805 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.7759. Min Act: -0.0000

Data Index: 1236752 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6595. Min Act: -0.0000

Data Index: 704344 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1272318 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1306386 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.4855. Min Act: -0.0000

Data Index: 295300 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.5958. Min Act: -0.0000

Data Index: 670708 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.6594. Min Act: -0.0000

Data Index: 261113 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1044950 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1109847 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.3799. Min Act: -0.0000

Data Index: 987031 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.4682. Min Act: -0.0000

Data Index: 839342 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1562861 (Python Code)

Max Activating Token Index: 954

Text #12

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.3147. Min Act: -0.0000

Data Index: 845893 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1248921 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.2959. Min Act: -0.0000

Data Index: 409270 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.3377. Min Act: -0.0000

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.2764. Min Act: -0.0000

Data Index: 950909 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.2640. Min Act: -0.0000

Data Index: 975647 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.1066. Min Act: -0.0000

Data Index: 328388 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.7759. Min Range: -1.7759

Max Act: 1.1586. Min Act: -0.0000

Data Index: 183737 (C4 (Web Text))

Max Activating Token Index: 433