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

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

Neuron 3839 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: 0.1127. Min Range: -0.1127

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1633370 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1042200 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0799. Min Act: -0.0000

Data Index: 269673 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1471727 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1268904 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0780. Min Act: -0.0000

Data Index: 243064 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0715. Min Act: -0.0000

Data Index: 180169 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0778. Min Act: -0.0000

Data Index: 686683 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0716. Min Act: -0.0000

Data Index: 588698 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0708. Min Act: -0.0000

Data Index: 673558 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1315967 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0617. Min Act: -0.0000

Data Index: 149440 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0559. Min Act: -0.0000

Data Index: 85191 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0612. Min Act: -0.0000

Data Index: 815986 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0612. Min Act: -0.0000

Data Index: 102464 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1638646 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1489712 (Python Code)

Max Activating Token Index: 248

Text #17

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1638985 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0574. Min Act: -0.0000

Data Index: 528622 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0546. Min Act: -0.0000

Data Index: 819071 (C4 (Web Text))

Max Activating Token Index: 567