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

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

Neuron 3670 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5934. Min Act: -0.0000

Data Index: 916259 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5621. Min Act: -0.0000

Data Index: 774033 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.5451. Min Act: -0.0000

Data Index: 410385 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1264932 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4544. Min Act: -0.0000

Data Index: 434919 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4145. Min Act: 0.0000

Data Index: 1242434 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4246. Min Act: -0.0000

Data Index: 213157 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4028. Min Act: -0.0000

Data Index: 839995 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4319. Min Act: -0.0000

Data Index: 420051 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4262. Min Act: -0.0000

Data Index: 836924 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4468. Min Act: -0.0000

Data Index: 915155 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1007989 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1162041 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1197790 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4160. Min Act: -0.0000

Data Index: 364308 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.4160. Min Act: -0.0000

Data Index: 979579 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3961. Min Act: -0.0000

Data Index: 105807 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3900. Min Act: -0.0000

Data Index: 211437 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3897. Min Act: -0.0000

Data Index: 430690 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 0.5934. Min Range: -0.5934

Max Act: 0.3724. Min Act: -0.0000

Data Index: 374094 (C4 (Web Text))

Max Activating Token Index: 95