Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3817 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.3120. Min Act: -0.0002

Data Index: 563502 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.2049. Min Act: -0.0002

Data Index: 469735 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1882. Min Act: -0.0002

Data Index: 279207 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1720. Min Act: -0.0002

Data Index: 508943 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1892. Min Act: -0.0002

Data Index: 742668 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1240. Min Act: -0.0002

Data Index: 1352941 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0559. Min Act: -0.0002

Data Index: 230177 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0134. Min Act: -0.0002

Data Index: 257086 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0707. Min Act: -0.0002

Data Index: 1155388 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0904. Min Act: -0.0002

Data Index: 889925 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1185. Min Act: -0.0002

Data Index: 398593 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1707. Min Act: -0.0002

Data Index: 437680 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0779. Min Act: -0.0002

Data Index: 828201 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0469. Min Act: -0.0002

Data Index: 50202 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0999. Min Act: -0.0002

Data Index: 364780 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1342. Min Act: -0.0002

Data Index: 714517 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0418. Min Act: -0.0002

Data Index: 382592 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0628. Min Act: -0.0002

Data Index: 1099596 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0877. Min Act: -0.0002

Data Index: 52909 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9961. Min Act: -0.0002

Data Index: 413735 (C4 (Web Text))

Max Activating Token Index: 113