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

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

Neuron 2058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.2048. Min Act: -0.0000

Data Index: 852381 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.2048. Min Range: -1.2048

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1325077 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.9727. Min Act: -0.0000

Data Index: 1348055 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.8680. Min Act: -0.0000

Data Index: 129002 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7904. Min Act: -0.0001

Data Index: 805966 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7571. Min Act: -0.0001

Data Index: 608788 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1239440 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7244. Min Act: -0.0000

Data Index: 350007 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7446. Min Act: -0.0001

Data Index: 1267466 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.7392. Min Act: -0.0001

Data Index: 254174 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6855. Min Act: -0.0000

Data Index: 968309 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6242. Min Act: -0.0000

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1309013 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6178. Min Act: -0.0001

Data Index: 1168913 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6180. Min Act: -0.0000

Data Index: 615879 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6337. Min Act: -0.0000

Data Index: 819103 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6082. Min Act: -0.0001

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1140510 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6574. Min Act: -0.0001

Data Index: 790461 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.2048. Min Range: -1.2048

Max Act: 0.6261. Min Act: -0.0000

Data Index: 476245 (C4 (Web Text))

Max Activating Token Index: 503