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

Dataset: The Pile

Neuron 2989 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: 1.6755. Min Range: -1.6755

Max Act: 1.5763. Min Act: -0.0000

Data Index: 473780 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.5784. Min Act: -0.0000

Data Index: 1767624 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1927248 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.6755. Min Act: -0.0000

Data Index: 810775 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.4127. Min Act: -0.0000

Data Index: 421727 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1170837 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1546 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.3730. Min Act: -0.0001

Data Index: 526504 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.4485. Min Act: -0.0000

Data Index: 173425 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.3534. Min Act: -0.0000

Data Index: 1823473 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.3392. Min Act: -0.0000

Data Index: 1678461 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.4906. Min Act: -0.0000

Data Index: 1710658 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.3194. Min Act: -0.0000

Data Index: 581677 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1757118 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.2514. Min Act: -0.0000

Data Index: 752324 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1016595 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.2726. Min Act: -0.0000

Data Index: 594669 (The Pile)

Max Activating Token Index: 670

Text #17

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.4170. Min Act: -0.0000

Data Index: 294872 (The Pile)

Max Activating Token Index: 230

Text #18

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.2468. Min Act: -0.0000

Data Index: 349456 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 1.6755. Min Range: -1.6755

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1861343 (The Pile)

Max Activating Token Index: 96