Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3997 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8484. Min Act: -0.0000

Data Index: 151942 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1850488 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8976. Min Act: -0.0000

Data Index: 570256 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8073. Min Act: -0.0000

Data Index: 305030 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1939142 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8132. Min Act: -0.0000

Data Index: 139805 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1155732 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1066451 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1297008 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7830. Min Act: -0.0000

Data Index: 856526 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7577. Min Act: -0.0000

Data Index: 161682 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1962909 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7285. Min Act: -0.0000

Data Index: 36375 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7246. Min Act: -0.0000

Data Index: 149699 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7309. Min Act: -0.0000

Data Index: 415607 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7101. Min Act: -0.0000

Data Index: 258363 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1713346 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1272414 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7448. Min Act: -0.0000

Data Index: 495306 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1871956 (The Pile)

Max Activating Token Index: 8