Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4041 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.4060. Min Act: -0.0000

Data Index: 559031 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.4024. Min Act: -0.0000

Data Index: 909404 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3959. Min Act: -0.0000

Data Index: 83030 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3586. Min Act: -0.0000

Data Index: 491846 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3147. Min Act: -0.0000

Data Index: 354298 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3314. Min Act: -0.0000

Data Index: 370828 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3206. Min Act: -0.0000

Data Index: 715927 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3110. Min Act: -0.0000

Data Index: 391068 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2988. Min Act: -0.0000

Data Index: 844529 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2913. Min Act: -0.0000

Data Index: 546804 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1166282 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2745. Min Act: -0.0000

Data Index: 851400 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2915. Min Act: -0.0000

Data Index: 1298087 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2813. Min Act: -0.0000

Data Index: 617094 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2722. Min Act: -0.0000

Data Index: 846371 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2670. Min Act: -0.0000

Data Index: 837885 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1226381 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1343937 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2506. Min Act: -0.0000

Data Index: 237464 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2447. Min Act: -0.0000

Data Index: 926862 (C4 (Web Text))

Max Activating Token Index: 919