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

Dataset: The Pile

Neuron 1489 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0000

Data Index: 611269 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0987. Min Act: -0.0000

Data Index: 951210 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0924. Min Act: -0.0000

Data Index: 946167 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0873. Min Act: -0.0001

Data Index: 652958 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1352937 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1113614 (The Pile)

Max Activating Token Index: 220

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0819. Min Act: -0.0001

Data Index: 849357 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1121588 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0733. Min Act: -0.0000

Data Index: 49532 (The Pile)

Max Activating Token Index: 209

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1085985 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1034029 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0777. Min Act: -0.0001

Data Index: 491483 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0753. Min Act: -0.0000

Data Index: 86603 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1668519 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0703. Min Act: -0.0000

Data Index: 480052 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0679. Min Act: -0.0000

Data Index: 706442 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1900612 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0622. Min Act: -0.0000

Data Index: 847957 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0623. Min Act: -0.0001

Data Index: 715643 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1859285 (The Pile)

Max Activating Token Index: 761