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

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

Neuron 3299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9267. Min Range: -3.9267

Max Act: 3.9267. Min Act: -0.0000

Data Index: 666677 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 3.9267. Min Range: -3.9267

Max Act: 3.1464. Min Act: -0.0000

Data Index: 1264260 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 3.9267. Min Range: -3.9267

Max Act: 3.0913. Min Act: -0.0000

Data Index: 1617612 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 3.9267. Min Range: -3.9267

Max Act: 3.0151. Min Act: -0.0000

Data Index: 1141645 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.5040. Min Act: -0.0000

Data Index: 809791 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.6834. Min Act: -0.0000

Data Index: 788009 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.6444. Min Act: -0.0000

Data Index: 688733 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.5656. Min Act: -0.0000

Data Index: 1621191 (Python Code)

Max Activating Token Index: 286

Text #8

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.5108. Min Act: -0.0000

Data Index: 236125 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.1194. Min Act: -0.0000

Data Index: 357147 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 3.9267. Min Range: -3.9267

Max Act: 3.1563. Min Act: -0.0000

Data Index: 7584 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.7040. Min Act: -0.0000

Data Index: 1432582 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.5587. Min Act: -0.0000

Data Index: 527864 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.5042. Min Act: -0.0000

Data Index: 1455973 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.3945. Min Act: -0.0000

Data Index: 1455861 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.6237. Min Act: -0.0000

Data Index: 1643504 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.3696. Min Act: -0.0000

Data Index: 607530 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.5817. Min Act: -0.0000

Data Index: 1655650 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.4239. Min Act: -0.0000

Data Index: 400075 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 3.9267. Min Range: -3.9267

Max Act: 2.4854. Min Act: -0.0000

Data Index: 1566332 (Python Code)

Max Activating Token Index: 204