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

Dataset: The Pile

Neuron 1726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6837. Min Act: -0.0000

Data Index: 858508 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.7094. Min Act: -0.0000

Data Index: 210253 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6445. Min Act: 0.0000

Data Index: 642434 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6319. Min Act: -0.0000

Data Index: 928671 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6737. Min Act: -0.0000

Data Index: 293864 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1752179 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5853. Min Act: -0.0000

Data Index: 989506 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1430258 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1884968 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5429. Min Act: -0.0000

Data Index: 790698 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1609065 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5327. Min Act: -0.0000

Data Index: 724351 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5537. Min Act: -0.0000

Data Index: 263856 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1370422 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1449231 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1406932 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5329. Min Act: -0.0000

Data Index: 864578 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1020756 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1146236 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5450. Min Act: -0.0000

Data Index: 134695 (The Pile)

Max Activating Token Index: 891