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

Dataset: The Pile

Neuron 3930 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: 1.6995. Min Range: -1.6995

Max Act: 1.5956. Min Act: -0.0000

Data Index: 592779 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.6995. Min Act: -0.0000

Data Index: 1625730 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5156. Min Act: -0.0000

Data Index: 939105 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1502070 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1591523 (The Pile)

Max Activating Token Index: 320

Text #5

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.5597. Min Act: -0.0000

Data Index: 770367 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.3128. Min Act: -0.0000

Data Index: 775114 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.3001. Min Act: -0.0000

Data Index: 858875 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1764062 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1539450 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 1.6995. Min Range: -1.6995

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1087755 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2366. Min Act: -0.0000

Data Index: 1629466 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1819331 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2868. Min Act: -0.0000

Data Index: 345280 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2492. Min Act: -0.0000

Data Index: 455519 (The Pile)

Max Activating Token Index: 863

Text #15

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1529. Min Act: -0.0000

Data Index: 433997 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1404664 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1024899 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.1052. Min Act: -0.0000

Data Index: 341549 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 1.6995. Min Range: -1.6995

Max Act: 1.0717. Min Act: -0.0000

Data Index: 380427 (The Pile)

Max Activating Token Index: 448