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

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

Neuron 3310 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3737. Min Act: -0.0001

Data Index: 170965 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1013875 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1298769 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1183348 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2315. Min Act: -0.0001

Data Index: 109998 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2427. Min Act: -0.0001

Data Index: 608832 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2342. Min Act: -0.0001

Data Index: 702348 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2270. Min Act: -0.0001

Data Index: 752955 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2211. Min Act: -0.0001

Data Index: 107440 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2047. Min Act: -0.0001

Data Index: 612439 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2178. Min Act: -0.0001

Data Index: 388745 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1009156 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2049. Min Act: -0.0001

Data Index: 602739 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1094225 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2109. Min Act: -0.0001

Data Index: 575052 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1989. Min Act: -0.0001

Data Index: 577178 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2072. Min Act: -0.0001

Data Index: 366117 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2069. Min Act: -0.0001

Data Index: 26338 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1904. Min Act: -0.0001

Data Index: 670957 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1837. Min Act: -0.0001

Data Index: 1018984 (C4 (Web Text))

Max Activating Token Index: 791