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

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

Neuron 2187 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.3481. Min Act: -0.0000

Data Index: 1472063 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.1912. Min Act: -0.0000

Data Index: 1632214 (Python Code)

Max Activating Token Index: 812

Text #2

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.1587. Min Act: -0.0000

Data Index: 1596743 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1438713 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.0726. Min Act: -0.0000

Data Index: 1509118 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1548850 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.0567. Min Act: -0.0000

Data Index: 1569717 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.0337. Min Act: -0.0000

Data Index: 300025 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.9021. Min Act: -0.0000

Data Index: 1573162 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.1297. Min Act: -0.0000

Data Index: 1580812 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.1251. Min Act: -0.0001

Data Index: 752137 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.9707. Min Act: -0.0000

Data Index: 1523689 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.8459. Min Act: -0.0000

Data Index: 555250 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.8175. Min Act: -0.0000

Data Index: 1478058 (Python Code)

Max Activating Token Index: 430

Text #14

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.8095. Min Act: -0.0001

Data Index: 71218 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 2.3481. Min Range: -2.3481

Max Act: 2.0299. Min Act: -0.0000

Data Index: 1440626 (Python Code)

Max Activating Token Index: 146

Text #16

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.9027. Min Act: -0.0000

Data Index: 1385710 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.8869. Min Act: -0.0000

Data Index: 1639195 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.7854. Min Act: -0.0000

Data Index: 1608143 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 2.3481. Min Range: -2.3481

Max Act: 1.8008. Min Act: -0.0000

Data Index: 1485154 (Python Code)

Max Activating Token Index: 312