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

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

Neuron 737 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: 5.6303. Min Range: -5.6303

Max Act: 5.6303. Min Act: -0.0000

Data Index: 839185 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.6723. Min Act: -0.0000

Data Index: 1497213 (Python Code)

Max Activating Token Index: 399

Text #2

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1109753 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.3668. Min Act: -0.0000

Data Index: 1653342 (Python Code)

Max Activating Token Index: 402

Text #4

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.1154. Min Act: -0.0000

Data Index: 49004 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.2171. Min Act: -0.0000

Data Index: 1411012 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1229556 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.1728. Min Act: -0.0000

Data Index: 444279 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.1854. Min Act: -0.0000

Data Index: 1227332 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.9561. Min Act: -0.0000

Data Index: 1093835 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 5.6303. Min Range: -5.6303

Max Act: 2.0397. Min Act: -0.0000

Data Index: 1372446 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.9623. Min Act: -0.0000

Data Index: 1172878 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.9336. Min Act: -0.0000

Data Index: 398938 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.9583. Min Act: -0.0000

Data Index: 830227 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1557726 (Python Code)

Max Activating Token Index: 119

Text #15

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.8090. Min Act: -0.0000

Data Index: 1399020 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.8099. Min Act: -0.0000

Data Index: 1651141 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1405405 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.9622. Min Act: -0.0000

Data Index: 1035107 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 5.6303. Min Range: -5.6303

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1004727 (C4 (Web Text))

Max Activating Token Index: 665