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

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

Neuron 3824 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1355020 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0628. Min Act: -0.0000

Data Index: 979164 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1083784 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0560. Min Act: -0.0000

Data Index: 561353 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1525616 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0597. Min Act: -0.0000

Data Index: 110242 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0524. Min Act: -0.0000

Data Index: 1646316 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1433777 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0557. Min Act: -0.0000

Data Index: 675326 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1036580 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1526790 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1544550 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1353981 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1424410 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1401701 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0514. Min Act: -0.0000

Data Index: 914229 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0526. Min Act: -0.0000

Data Index: 178486 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0506. Min Act: -0.0000

Data Index: 206882 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1288044 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0499. Min Act: -0.0000

Data Index: 749879 (C4 (Web Text))

Max Activating Token Index: 84