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

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

Neuron 1326 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1554572 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1022. Min Act: -0.0000

Data Index: 923874 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1034. Min Act: -0.0000

Data Index: 782537 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0924. Min Act: -0.0000

Data Index: 735614 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0895. Min Act: -0.0000

Data Index: 260492 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0875. Min Act: -0.0000

Data Index: 735029 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0872. Min Act: -0.0000

Data Index: 501145 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0851. Min Act: -0.0000

Data Index: 864002 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1111185 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0792. Min Act: -0.0000

Data Index: 773195 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0716. Min Act: -0.0000

Data Index: 266737 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1170795 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1171937 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1651582 (Python Code)

Max Activating Token Index: 401

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1127074 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1096172 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0705. Min Act: -0.0001

Data Index: 126112 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0715. Min Act: -0.0000

Data Index: 696861 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1465507 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0692. Min Act: -0.0000

Data Index: 412846 (C4 (Web Text))

Max Activating Token Index: 681