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

Dataset: The Pile

Neuron 540 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: 0.4081. Min Range: -0.4081

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1121718 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.4081. Min Act: -0.0000

Data Index: 204294 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3602. Min Act: -0.0000

Data Index: 510955 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3690. Min Act: -0.0000

Data Index: 295419 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1329231 (The Pile)

Max Activating Token Index: 824

Text #5

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3377. Min Act: -0.0000

Data Index: 613560 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3768. Min Act: -0.0000

Data Index: 386721 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3359. Min Act: -0.0000

Data Index: 502224 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1355564 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2959. Min Act: -0.0000

Data Index: 74079 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2921. Min Act: -0.0000

Data Index: 88271 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2994. Min Act: -0.0000

Data Index: 583835 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3051. Min Act: -0.0000

Data Index: 175856 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3099. Min Act: -0.0000

Data Index: 634726 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2906. Min Act: -0.0000

Data Index: 239274 (The Pile)

Max Activating Token Index: 20

Text #15

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1577222 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2373. Min Act: -0.0000

Data Index: 248800 (The Pile)

Max Activating Token Index: 896

Text #17

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2858. Min Act: -0.0000

Data Index: 770323 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.3684. Min Act: -0.0000

Data Index: 822775 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 0.4081. Min Range: -0.4081

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1280229 (The Pile)

Max Activating Token Index: 333