Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1980 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1705211 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1370586 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4272. Min Act: -0.0000

Data Index: 388927 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1125008 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4163. Min Act: -0.0000

Data Index: 21924 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3909. Min Act: -0.0001

Data Index: 1015894 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3603. Min Act: -0.0000

Data Index: 680716 (The Pile)

Max Activating Token Index: 270

Text #7

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1851560 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3456. Min Act: -0.0000

Data Index: 19810 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3592. Min Act: -0.0000

Data Index: 103215 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1248909 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1856957 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3541. Min Act: -0.0000

Data Index: 739251 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3630. Min Act: -0.0000

Data Index: 276427 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3477. Min Act: -0.0000

Data Index: 822112 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1274332 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3695. Min Act: -0.0000

Data Index: 313086 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3406. Min Act: -0.0000

Data Index: 156921 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3522. Min Act: -0.0000

Data Index: 670113 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1188030 (The Pile)

Max Activating Token Index: 218