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

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

Neuron 2424 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.4184. Min Act: -0.0000

Data Index: 1480839 (Python Code)

Max Activating Token Index: 773

Text #1

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.3983. Min Act: -0.0000

Data Index: 1370222 (Python Code)

Max Activating Token Index: 169

Text #2

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.1788. Min Act: -0.0000

Data Index: 1410737 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.2624. Min Act: -0.0000

Data Index: 1469111 (Python Code)

Max Activating Token Index: 937

Text #4

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.0524. Min Act: -0.0000

Data Index: 1503754 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 2.4184. Min Range: -2.4184

Max Act: 2.0116. Min Act: -0.0000

Data Index: 1600813 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.9624. Min Act: -0.0000

Data Index: 1377137 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1604689 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.9252. Min Act: -0.0000

Data Index: 1508580 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8114. Min Act: -0.0000

Data Index: 1576815 (Python Code)

Max Activating Token Index: 920

Text #10

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7726. Min Act: -0.0000

Data Index: 1556133 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7542. Min Act: -0.0000

Data Index: 1381551 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8193. Min Act: -0.0000

Data Index: 907490 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1551700 (Python Code)

Max Activating Token Index: 766

Text #14

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.8007. Min Act: -0.0000

Data Index: 1499120 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1461971 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.5873. Min Act: -0.0000

Data Index: 1363521 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.6695. Min Act: -0.0000

Data Index: 1603334 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.7656. Min Act: -0.0000

Data Index: 1470234 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 2.4184. Min Range: -2.4184

Max Act: 1.6459. Min Act: -0.0000

Data Index: 1576804 (Python Code)

Max Activating Token Index: 817