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

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

Neuron 3429 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: 1.8067. Min Range: -1.8067

Max Act: 1.7519. Min Act: -0.0000

Data Index: 63000 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.8067. Min Act: -0.0000

Data Index: 882832 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.7275. Min Act: -0.0000

Data Index: 701112 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.7325. Min Act: -0.0001

Data Index: 535433 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.7393. Min Act: -0.0000

Data Index: 553565 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1092116 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.6250. Min Act: -0.0000

Data Index: 418347 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5568. Min Act: -0.0000

Data Index: 308805 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5841. Min Act: -0.0000

Data Index: 1078057 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5604. Min Act: -0.0000

Data Index: 895670 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5923. Min Act: -0.0000

Data Index: 976435 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1219834 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5735. Min Act: -0.0000

Data Index: 365486 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1328583 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5159. Min Act: -0.0000

Data Index: 975226 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.4821. Min Act: -0.0000

Data Index: 577185 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5386. Min Act: -0.0000

Data Index: 687025 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.4056. Min Act: -0.0000

Data Index: 1246093 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.5664. Min Act: -0.0000

Data Index: 279957 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.8067. Min Range: -1.8067

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1094668 (C4 (Web Text))

Max Activating Token Index: 591