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

Dataset: The Pile

Neuron 5031 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: 1.3086. Min Range: -1.3086

Max Act: 1.1736. Min Act: -0.0000

Data Index: 876411 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1102023 (The Pile)

Max Activating Token Index: 861

Text #2

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0780. Min Act: 0.0000

Data Index: 1952895 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1782766 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8320. Min Act: -0.0000

Data Index: 52089 (The Pile)

Max Activating Token Index: 684

Text #5

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0566. Min Act: -0.0000

Data Index: 774556 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1299840 (The Pile)

Max Activating Token Index: 15

Text #7

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1441081 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9769. Min Act: 0.0000

Data Index: 574405 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1268340 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8834. Min Act: 0.0000

Data Index: 1868760 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8580. Min Act: -0.0000

Data Index: 786082 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9902. Min Act: 0.0000

Data Index: 1567364 (The Pile)

Max Activating Token Index: 386

Text #13

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1459653 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1150871 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1084127 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8548. Min Act: -0.0000

Data Index: 715912 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1502233 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.8308. Min Act: -0.0000

Data Index: 300267 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1813428 (The Pile)

Max Activating Token Index: 342