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

Dataset: The Pile

Neuron 1539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.8080. Min Act: -0.0000

Data Index: 246019 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1803750 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.4855. Min Act: -0.0000

Data Index: 1832340 (The Pile)

Max Activating Token Index: 791

Text #3

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.3454. Min Act: -0.0000

Data Index: 936285 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.3089. Min Act: -0.0000

Data Index: 227645 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.3720. Min Act: -0.0000

Data Index: 333266 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.2223. Min Act: -0.0000

Data Index: 267302 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.1339. Min Act: -0.0000

Data Index: 53815 (The Pile)

Max Activating Token Index: 761

Text #8

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.1190. Min Act: -0.0000

Data Index: 136285 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1604223 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1581185 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.8080. Min Range: -1.8080

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1295391 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.1010. Min Act: -0.0000

Data Index: 847062 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.0831. Min Act: -0.0000

Data Index: 980363 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 1.8080. Min Range: -1.8080

Max Act: 0.9499. Min Act: -0.0000

Data Index: 578423 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.2408. Min Act: -0.0000

Data Index: 433011 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.0895. Min Act: -0.0000

Data Index: 481679 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1943611 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1569189 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 1.8080. Min Range: -1.8080

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1807739 (The Pile)

Max Activating Token Index: 204