Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 174 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0158. Min Act: -0.0006

Data Index: 79509 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0111. Min Act: -0.0006

Data Index: 765360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0107. Min Act: -0.0006

Data Index: 898526 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1315198 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1224096 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0097. Min Act: -0.0006

Data Index: 313629 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1047629 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1195400 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0094. Min Act: -0.0006

Data Index: 906897 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1308989 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1358442 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1153511 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0091. Min Act: -0.0006

Data Index: 69630 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1094162 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1065255 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0086. Min Act: -0.0006

Data Index: 219862 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0085. Min Act: -0.0006

Data Index: 20050 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0085. Min Act: -0.0006

Data Index: 656904 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0084. Min Act: -0.0006

Data Index: 767706 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0158. Min Range: -0.0158

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1019427 (C4 (Web Text))

Max Activating Token Index: 868