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

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

Neuron 3550 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 433324 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0060. Min Act: -0.0002

Data Index: 887335 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0058. Min Act: -0.0002

Data Index: 728894 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 246253 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 976399 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1271250 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 604457 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1039321 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0056. Min Act: -0.0002

Data Index: 688033 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 183706 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0055. Min Act: -0.0002

Data Index: 512360 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1150597 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 271065 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1347981 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 757438 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 49550 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1221132 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 383981 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 590227 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.0060. Min Range: -0.0060

Max Act: 0.0054. Min Act: -0.0002

Data Index: 1067989 (C4 (Web Text))

Max Activating Token Index: 401