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

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

Neuron 240 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: 0.2069. Min Range: -0.2069

Max Act: 0.2069. Min Act: -0.0000

Data Index: 752485 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1239. Min Act: -0.0000

Data Index: 228801 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1250. Min Act: 0.0000

Data Index: 1474611 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1280. Min Act: -0.0000

Data Index: 796536 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1542172 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1365966 (Python Code)

Max Activating Token Index: 982

Text #6

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1552205 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1053. Min Act: -0.0000

Data Index: 231991 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1036. Min Act: -0.0000

Data Index: 582220 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1061. Min Act: 0.0000

Data Index: 1611661 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1479337 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1423266 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1055. Min Act: 0.0000

Data Index: 92417 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1618610 (Python Code)

Max Activating Token Index: 589

Text #14

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1015. Min Act: -0.0000

Data Index: 453557 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1006. Min Act: 0.0000

Data Index: 1541556 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1448400 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1508214 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1015472 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1007. Min Act: -0.0000

Data Index: 523355 (C4 (Web Text))

Max Activating Token Index: 912