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

Dataset: The Pile

Neuron 3544 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1305146 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9521. Min Act: -0.0000

Data Index: 353060 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8180. Min Act: -0.0000

Data Index: 867324 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1733903 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 1.0039. Min Range: -1.0039

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1907709 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9533. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1468652 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1467883 (The Pile)

Max Activating Token Index: 901

Text #9

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1415795 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.6670. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.7061. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.6117. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1527254 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.6216. Min Act: -0.0000

Data Index: 600772 (The Pile)

Max Activating Token Index: 67

Text #17

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1093652 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.0039. Min Range: -1.0039

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1674626 (The Pile)

Max Activating Token Index: 180