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

Dataset: The Pile

Neuron 1945 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.7468. Min Act: -0.0000

Data Index: 811283 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.7288. Min Act: -0.0000

Data Index: 534968 (The Pile)

Max Activating Token Index: 368

Text #2

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.7632. Min Act: -0.0000

Data Index: 921456 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.6754. Min Act: -0.0000

Data Index: 807259 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.5741. Min Act: -0.0000

Data Index: 815990 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.5738. Min Act: -0.0000

Data Index: 358042 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4619. Min Act: -0.0000

Data Index: 651729 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4141. Min Act: -0.0000

Data Index: 839989 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4902. Min Act: -0.0000

Data Index: 1172617 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1119275 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4670. Min Act: -0.0000

Data Index: 629730 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1847758 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4995. Min Act: -0.0000

Data Index: 1968116 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1311208 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.3876. Min Act: -0.0000

Data Index: 524814 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.4595. Min Act: -0.0000

Data Index: 101692 (The Pile)

Max Activating Token Index: 747

Text #16

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.3608. Min Act: -0.0000

Data Index: 644375 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1880724 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.3699. Min Act: -0.0000

Data Index: 571218 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 1.7632. Min Range: -1.7632

Max Act: 1.2003. Min Act: -0.0000

Data Index: 304245 (The Pile)

Max Activating Token Index: 206