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

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

Neuron 440 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2839. Min Act: -0.0000

Data Index: 634209 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1294340 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1338764 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2943. Min Act: -0.0000

Data Index: 768731 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2741. Min Act: -0.0000

Data Index: 279347 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2499. Min Act: -0.0000

Data Index: 666442 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2631. Min Act: -0.0000

Data Index: 993154 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1093346 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2208. Min Act: -0.0000

Data Index: 963380 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2252. Min Act: -0.0000

Data Index: 761026 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1985. Min Act: -0.0000

Data Index: 426565 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2336. Min Act: -0.0000

Data Index: 513685 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2244. Min Act: -0.0000

Data Index: 279913 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2092. Min Act: -0.0000

Data Index: 875361 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1881. Min Act: -0.0000

Data Index: 572941 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1001389 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2226. Min Act: -0.0000

Data Index: 23306 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2068. Min Act: -0.0000

Data Index: 21158 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.1979. Min Act: -0.0000

Data Index: 498312 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.2984. Min Range: -0.2984

Max Act: 0.2078. Min Act: -0.0000

Data Index: 153885 (C4 (Web Text))

Max Activating Token Index: 290