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

Dataset: The Pile

Neuron 4525 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: 4.0356. Min Range: -4.0356

Max Act: 3.7208. Min Act: -0.0000

Data Index: 1544283 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0356. Min Act: -0.0000

Data Index: 1575330 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.9157. Min Act: -0.0000

Data Index: 210942 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.3850. Min Act: -0.0000

Data Index: 761251 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 4.0356. Min Range: -4.0356

Max Act: 4.0008. Min Act: -0.0000

Data Index: 296743 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.6386. Min Act: -0.0000

Data Index: 1869797 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.0133. Min Act: -0.0000

Data Index: 1789202 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.2870. Min Act: -0.0000

Data Index: 922453 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.0191. Min Act: -0.0000

Data Index: 489129 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.4508. Min Act: -0.0000

Data Index: 1458658 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.5225. Min Act: -0.0000

Data Index: 1672417 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.3749. Min Act: -0.0000

Data Index: 1435136 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.2953. Min Act: -0.0000

Data Index: 500829 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.6169. Min Act: -0.0000

Data Index: 1020409 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.4441. Min Act: -0.0000

Data Index: 1777458 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.6970. Min Act: -0.0000

Data Index: 1501690 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 4.0356. Min Range: -4.0356

Max Act: 2.9428. Min Act: -0.0000

Data Index: 1931918 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.1615. Min Act: -0.0000

Data Index: 1420783 (The Pile)

Max Activating Token Index: 20

Text #18

Max Range: 4.0356. Min Range: -4.0356

Max Act: 2.7006. Min Act: -0.0000

Data Index: 1992363 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 4.0356. Min Range: -4.0356

Max Act: 3.1042. Min Act: -0.0000

Data Index: 1476805 (The Pile)

Max Activating Token Index: 835