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

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

Neuron 1984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1324. Min Act: -0.0000

Data Index: 983080 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1312. Min Act: -0.0001

Data Index: 314585 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1138. Min Act: -0.0000

Data Index: 396956 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1055. Min Act: -0.0001

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1149652 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1147580 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1126. Min Act: -0.0000

Data Index: 611727 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1028. Min Act: -0.0000

Data Index: 69346 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0972. Min Act: -0.0000

Data Index: 20077 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0978. Min Act: -0.0001

Data Index: 66508 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1061. Min Act: -0.0000

Data Index: 924065 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0988. Min Act: -0.0000

Data Index: 484883 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0949. Min Act: -0.0001

Data Index: 942104 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0971. Min Act: -0.0001

Data Index: 465854 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1355805 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0942. Min Act: -0.0001

Data Index: 488499 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0925. Min Act: -0.0000

Data Index: 122075 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0832. Min Act: -0.0000

Data Index: 652334 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0927. Min Act: -0.0001

Data Index: 499018 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0886. Min Act: -0.0001

Data Index: 335010 (C4 (Web Text))

Max Activating Token Index: 420