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

Dataset: The Pile

Neuron 35 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7623. Min Act: -0.0000

Data Index: 1167445 (The Pile)

Max Activating Token Index: 217

Text #1

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.8707. Min Act: -0.0000

Data Index: 74501 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1310541 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1767738 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7688. Min Act: -0.0000

Data Index: 355351 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7591. Min Act: -0.0000

Data Index: 714847 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7562. Min Act: -0.0000

Data Index: 371538 (The Pile)

Max Activating Token Index: 360

Text #7

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.8205. Min Act: -0.0000

Data Index: 1988142 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1434844 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6968. Min Act: -0.0000

Data Index: 1980381 (The Pile)

Max Activating Token Index: 705

Text #10

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7882. Min Act: -0.0000

Data Index: 583122 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6796. Min Act: -0.0000

Data Index: 1500257 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6678. Min Act: -0.0000

Data Index: 22139 (The Pile)

Max Activating Token Index: 271

Text #13

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.5639. Min Act: -0.0000

Data Index: 1510782 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1375547 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.5228. Min Act: -0.0000

Data Index: 568068 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6158. Min Act: -0.0000

Data Index: 1627125 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1904874 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.5953. Min Act: -0.0000

Data Index: 615288 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.8707. Min Range: -1.8707

Max Act: 1.6043. Min Act: -0.0000

Data Index: 406354 (The Pile)

Max Activating Token Index: 236