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

Dataset: The Pile

Neuron 741 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3796. Min Act: -0.0000

Data Index: 383721 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3747. Min Act: -0.0000

Data Index: 785286 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2512. Min Act: -0.0000

Data Index: 149013 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1053999 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1382689 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1970612 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1586303 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2728. Min Act: -0.0000

Data Index: 192469 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1068885 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1891679 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1963. Min Act: -0.0000

Data Index: 1952178 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1668970 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2937. Min Act: -0.0000

Data Index: 810113 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2724. Min Act: -0.0000

Data Index: 701829 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1834. Min Act: -0.0000

Data Index: 826502 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1963732 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1731. Min Act: -0.0000

Data Index: 555316 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.1338. Min Act: -0.0000

Data Index: 973603 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2179. Min Act: -0.0000

Data Index: 215225 (The Pile)

Max Activating Token Index: 730

Text #19

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.2246. Min Act: -0.0000

Data Index: 363940 (The Pile)

Max Activating Token Index: 60