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

Dataset: The Pile

Neuron 1985 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: 1.2297. Min Range: -1.2297

Max Act: 1.2297. Min Act: -0.0000

Data Index: 543455 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0519. Min Act: -0.0000

Data Index: 782466 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9848. Min Act: -0.0000

Data Index: 217906 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1717143 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1053719 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8821. Min Act: -0.0000

Data Index: 788571 (The Pile)

Max Activating Token Index: 296

Text #6

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1688222 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1053242 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1816836 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8090. Min Act: -0.0000

Data Index: 259085 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8052. Min Act: -0.0000

Data Index: 88696 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1954303 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7566. Min Act: -0.0000

Data Index: 165409 (The Pile)

Max Activating Token Index: 197

Text #13

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1514198 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7435. Min Act: -0.0000

Data Index: 850370 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1712387 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7340. Min Act: -0.0000

Data Index: 577265 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.6571. Min Act: -0.0000

Data Index: 219312 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7409. Min Act: -0.0000

Data Index: 811961 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1325574 (The Pile)

Max Activating Token Index: 154