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

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

Neuron 3224 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: 2.1779. Min Range: -2.1779

Max Act: 2.1779. Min Act: -0.0000

Data Index: 1467416 (Python Code)

Max Activating Token Index: 738

Text #1

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.9565. Min Act: -0.0000

Data Index: 1460765 (Python Code)

Max Activating Token Index: 968

Text #2

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.8736. Min Act: -0.0000

Data Index: 570577 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.7457. Min Act: -0.0000

Data Index: 1527625 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.9023. Min Act: -0.0000

Data Index: 479174 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1047822 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.6391. Min Act: -0.0000

Data Index: 537787 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.6371. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.6148. Min Act: -0.0000

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.4960. Min Act: -0.0000

Data Index: 1002682 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1307865 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.6534. Min Act: -0.0000

Data Index: 196555 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.5410. Min Act: -0.0000

Data Index: 617505 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.4503. Min Act: -0.0000

Data Index: 558711 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.6271. Min Act: -0.0000

Data Index: 903159 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.5924. Min Act: -0.0000

Data Index: 389694 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.5932. Min Act: -0.0000

Data Index: 59455 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.4654. Min Act: -0.0000

Data Index: 808135 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.3629. Min Act: -0.0000

Data Index: 92204 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 2.1779. Min Range: -2.1779

Max Act: 1.4569. Min Act: -0.0000

Data Index: 1305062 (C4 (Web Text))

Max Activating Token Index: 46