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

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

Neuron 3838 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: 2.2368. Min Range: -2.2368

Max Act: 2.0335. Min Act: -0.0000

Data Index: 811626 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 2.2368. Min Range: -2.2368

Max Act: 2.0877. Min Act: -0.0000

Data Index: 13555 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 2.2368. Min Range: -2.2368

Max Act: 2.2368. Min Act: -0.0000

Data Index: 343733 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.9867. Min Act: -0.0000

Data Index: 688467 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.9887. Min Act: -0.0000

Data Index: 1312590 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.9748. Min Act: -0.0000

Data Index: 293852 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.8299. Min Act: -0.0000

Data Index: 177050 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.7632. Min Act: -0.0000

Data Index: 112750 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.7343. Min Act: -0.0000

Data Index: 192329 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.6498. Min Act: -0.0000

Data Index: 455951 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.5721. Min Act: -0.0000

Data Index: 1027977 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1085189 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.6079. Min Act: -0.0000

Data Index: 586695 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.6413. Min Act: -0.0000

Data Index: 1159669 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.5549. Min Act: -0.0000

Data Index: 396506 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.4924. Min Act: -0.0000

Data Index: 985324 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.3581. Min Act: -0.0000

Data Index: 1008394 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1056141 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.4046. Min Act: -0.0000

Data Index: 156244 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 2.2368. Min Range: -2.2368

Max Act: 1.1118. Min Act: -0.0000

Data Index: 301544 (C4 (Web Text))

Max Activating Token Index: 780