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

Dataset: The Pile

Neuron 2352 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.2972. Min Range: -5.2972

Max Act: 5.2972. Min Act: -0.0000

Data Index: 97168 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.9441. Min Act: -0.0000

Data Index: 1159262 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 5.2972. Min Range: -5.2972

Max Act: 5.0022. Min Act: -0.0000

Data Index: 107303 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.7475. Min Act: -0.0000

Data Index: 962933 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.6843. Min Act: -0.0000

Data Index: 1412292 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.5718. Min Act: -0.0000

Data Index: 108228 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.6365. Min Act: -0.0000

Data Index: 55443 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.1417. Min Act: -0.0000

Data Index: 530744 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.4673. Min Act: -0.0000

Data Index: 1068071 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.2758. Min Act: -0.0000

Data Index: 30077 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.3335. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.3338. Min Act: -0.0000

Data Index: 408393 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.3391. Min Act: -0.0000

Data Index: 1430583 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.0676. Min Act: -0.0000

Data Index: 760448 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.4632. Min Act: -0.0000

Data Index: 1354023 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.2325. Min Act: -0.0000

Data Index: 721035 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 5.2972. Min Range: -5.2972

Max Act: 3.8370. Min Act: -0.0000

Data Index: 19437 (The Pile)

Max Activating Token Index: 180

Text #17

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.1823. Min Act: -0.0000

Data Index: 944252 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.4983. Min Act: -0.0000

Data Index: 1174556 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 5.2972. Min Range: -5.2972

Max Act: 4.0827. Min Act: -0.0000

Data Index: 1512755 (The Pile)

Max Activating Token Index: 340