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

Dataset: The Pile

Neuron 4275 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1270716 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8020. Min Act: -0.0000

Data Index: 333804 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.8054. Min Act: -0.0000

Data Index: 142606 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7499. Min Act: -0.0000

Data Index: 781336 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7516. Min Act: -0.0000

Data Index: 245598 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1770458 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.7432. Min Act: -0.0000

Data Index: 107109 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6632. Min Act: -0.0000

Data Index: 16255 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6518. Min Act: -0.0000

Data Index: 795533 (The Pile)

Max Activating Token Index: 7

Text #9

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1181369 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1335239 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6318. Min Act: -0.0000

Data Index: 376089 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6576. Min Act: -0.0000

Data Index: 453246 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1016402 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5963. Min Act: -0.0000

Data Index: 690933 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1494765 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5930. Min Act: -0.0000

Data Index: 9141 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1794073 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1430353 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 0.9028. Min Range: -0.9028

Max Act: 0.5941. Min Act: -0.0000

Data Index: 901541 (The Pile)

Max Activating Token Index: 528