Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1881397 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3725. Min Act: -0.0000

Data Index: 699393 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3904. Min Act: -0.0000

Data Index: 830939 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1643065 (The Pile)

Max Activating Token Index: 926

Text #4

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3095. Min Act: -0.0000

Data Index: 783992 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1050434 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1020962 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3177. Min Act: -0.0000

Data Index: 8451 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2909. Min Act: -0.0000

Data Index: 697847 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3202. Min Act: -0.0000

Data Index: 993786 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1004704 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2602. Min Act: 0.0000

Data Index: 841668 (The Pile)

Max Activating Token Index: 624

Text #12

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2947. Min Act: -0.0000

Data Index: 426315 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1240211 (The Pile)

Max Activating Token Index: 887

Text #14

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2832. Min Act: -0.0000

Data Index: 370757 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1653199 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2632. Min Act: -0.0000

Data Index: 304559 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1792434 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2692. Min Act: 0.0000

Data Index: 1965260 (The Pile)

Max Activating Token Index: 679

Text #19

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2698. Min Act: -0.0000

Data Index: 39357 (The Pile)

Max Activating Token Index: 452