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

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

Neuron 3635 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: 0.8958. Min Range: -0.8958

Max Act: 0.8958. Min Act: -0.0000

Data Index: 6467 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1235345 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8155. Min Act: -0.0000

Data Index: 475320 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8791. Min Act: -0.0000

Data Index: 748153 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7776. Min Act: -0.0000

Data Index: 886860 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8502. Min Act: -0.0000

Data Index: 762427 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1314179 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1318425 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1351405 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7381. Min Act: -0.0000

Data Index: 453632 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7641. Min Act: -0.0000

Data Index: 536140 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7326. Min Act: -0.0000

Data Index: 768048 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7027. Min Act: -0.0000

Data Index: 899842 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7019. Min Act: -0.0000

Data Index: 287781 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1263107 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6823. Min Act: -0.0000

Data Index: 704904 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7075. Min Act: -0.0000

Data Index: 81591 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.7037. Min Act: -0.0000

Data Index: 620582 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6585. Min Act: -0.0000

Data Index: 233689 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.8958. Min Range: -0.8958

Max Act: 0.6944. Min Act: -0.0000

Data Index: 195053 (C4 (Web Text))

Max Activating Token Index: 241