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

Dataset: The Pile

Neuron 895 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: 0.6408. Min Range: -0.6408

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1868276 (The Pile)

Max Activating Token Index: 275

Text #1

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1493347 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.6054. Min Act: -0.0000

Data Index: 693980 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1221678 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.5290. Min Act: -0.0000

Data Index: 492121 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4631. Min Act: -0.0000

Data Index: 990832 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1638453 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1097032 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4495. Min Act: -0.0000

Data Index: 616882 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4306. Min Act: -0.0000

Data Index: 784327 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4358. Min Act: -0.0000

Data Index: 875926 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1958490 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4006. Min Act: -0.0000

Data Index: 260734 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1825952 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1397067 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1511066 (The Pile)

Max Activating Token Index: 872

Text #16

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1105504 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1251533 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1008642 (The Pile)

Max Activating Token Index: 625

Text #19

Max Range: 0.6408. Min Range: -0.6408

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1520581 (The Pile)

Max Activating Token Index: 923