Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 347 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0462. Min Range: -3.0462

Max Act: 3.0462. Min Act: -0.0000

Data Index: 793842 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 3.0462. Min Range: -3.0462

Max Act: 2.3997. Min Act: -0.0000

Data Index: 1000656 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.0462. Min Range: -3.0462

Max Act: 2.4840. Min Act: -0.0000

Data Index: 182768 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 3.0462. Min Range: -3.0462

Max Act: 2.4482. Min Act: 0.0000

Data Index: 1027395 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 3.0462. Min Range: -3.0462

Max Act: 2.3627. Min Act: -0.0000

Data Index: 1213669 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 3.0462. Min Range: -3.0462

Max Act: 2.1044. Min Act: -0.0000

Data Index: 1126026 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.9428. Min Act: 0.0000

Data Index: 1345118 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6814. Min Act: -0.0000

Data Index: 1075546 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.7724. Min Act: -0.0000

Data Index: 1297244 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1327742 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6635. Min Act: -0.0000

Data Index: 593913 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.7572. Min Act: -0.0000

Data Index: 251636 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6597. Min Act: -0.0000

Data Index: 427012 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.7472. Min Act: -0.0000

Data Index: 1058858 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6852. Min Act: -0.0000

Data Index: 949659 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.8590. Min Act: -0.0000

Data Index: 646315 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.5638. Min Act: -0.0000

Data Index: 1352518 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6184. Min Act: -0.0000

Data Index: 359632 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6087. Min Act: -0.0000

Data Index: 459177 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 3.0462. Min Range: -3.0462

Max Act: 1.6929. Min Act: -0.0000

Data Index: 58741 (C4 (Web Text))

Max Activating Token Index: 936