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

Dataset: The Pile

Neuron 840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.2628. Min Act: -0.0000

Data Index: 491223 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.0488. Min Act: -0.0000

Data Index: 548967 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1897. Min Act: -0.0000

Data Index: 263886 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.1587. Min Act: -0.0000

Data Index: 1940901 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 3.2628. Min Range: -3.2628

Max Act: 3.0111. Min Act: -0.0000

Data Index: 1341491 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.9823. Min Act: -0.0000

Data Index: 602202 (The Pile)

Max Activating Token Index: 495

Text #6

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.8317. Min Act: -0.0000

Data Index: 1218983 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.9722. Min Act: -0.0000

Data Index: 1615323 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.9110. Min Act: -0.0000

Data Index: 1102577 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.8780. Min Act: -0.0000

Data Index: 1815301 (The Pile)

Max Activating Token Index: 490

Text #10

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.9716. Min Act: -0.0000

Data Index: 931284 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.8217. Min Act: -0.0000

Data Index: 197073 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1695337 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.6680. Min Act: -0.0000

Data Index: 378020 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.9270. Min Act: -0.0000

Data Index: 963106 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.6580. Min Act: -0.0000

Data Index: 397895 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.7323. Min Act: -0.0000

Data Index: 1281440 (The Pile)

Max Activating Token Index: 239

Text #17

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.7123. Min Act: -0.0000

Data Index: 1982897 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.7081. Min Act: -0.0000

Data Index: 89295 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 3.2628. Min Range: -3.2628

Max Act: 2.6958. Min Act: -0.0000

Data Index: 1261995 (The Pile)

Max Activating Token Index: 62