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

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

Neuron 550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1354. Min Act: -0.0000

Data Index: 465297 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1111. Min Act: -0.0000

Data Index: 6257 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1035. Min Act: -0.0000

Data Index: 423480 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1038. Min Act: -0.0000

Data Index: 222699 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1039. Min Act: -0.0000

Data Index: 421963 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1002. Min Act: -0.0000

Data Index: 402146 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1162285 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0977. Min Act: -0.0000

Data Index: 317317 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0966. Min Act: -0.0000

Data Index: 617067 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0970. Min Act: -0.0000

Data Index: 780897 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1010582 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0948. Min Act: -0.0000

Data Index: 59744 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0923. Min Act: -0.0000

Data Index: 760225 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0952. Min Act: -0.0000

Data Index: 61768 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1197890 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0843. Min Act: -0.0000

Data Index: 865352 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0869. Min Act: -0.0000

Data Index: 449332 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0840. Min Act: -0.0000

Data Index: 632904 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1117090 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1073284 (C4 (Web Text))

Max Activating Token Index: 329