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

Dataset: The Pile

Neuron 1397 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: 1.2661. Min Range: -1.2661

Max Act: 1.2661. Min Act: -0.0000

Data Index: 1075369 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.6456. Min Act: -0.0000

Data Index: 67946 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.6077. Min Act: 0.0000

Data Index: 625161 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5323. Min Act: -0.0000

Data Index: 869933 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1878961 (The Pile)

Max Activating Token Index: 1017

Text #5

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5074. Min Act: -0.0000

Data Index: 579019 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1141071 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5246. Min Act: -0.0000

Data Index: 963582 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5033. Min Act: -0.0000

Data Index: 533684 (The Pile)

Max Activating Token Index: 780

Text #9

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4964. Min Act: -0.0000

Data Index: 807853 (The Pile)

Max Activating Token Index: 964

Text #10

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5119. Min Act: -0.0000

Data Index: 403609 (The Pile)

Max Activating Token Index: 27

Text #11

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1831146 (The Pile)

Max Activating Token Index: 835

Text #12

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1985550 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.5013. Min Act: -0.0000

Data Index: 612656 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4812. Min Act: 0.0000

Data Index: 1366343 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1498469 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4478. Min Act: 0.0000

Data Index: 1547849 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4752. Min Act: -0.0000

Data Index: 377140 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4681. Min Act: 0.0000

Data Index: 1015274 (The Pile)

Max Activating Token Index: 904

Text #19

Max Range: 1.2661. Min Range: -1.2661

Max Act: 0.4849. Min Act: -0.0000

Data Index: 399247 (The Pile)

Max Activating Token Index: 101