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

Dataset: The Pile

Neuron 4670 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: 3.9418. Min Range: -3.9418

Max Act: 3.9418. Min Act: -0.0000

Data Index: 1941939 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.7665. Min Act: -0.0000

Data Index: 546255 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.6476. Min Act: -0.0000

Data Index: 415640 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.6308. Min Act: -0.0000

Data Index: 1703691 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.2764. Min Act: -0.0000

Data Index: 896844 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.3868. Min Act: -0.0000

Data Index: 713939 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.3625. Min Act: -0.0000

Data Index: 1473168 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.3233. Min Act: -0.0000

Data Index: 1346251 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.1646. Min Act: -0.0000

Data Index: 1271047 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 3.9418. Min Range: -3.9418

Max Act: 2.8834. Min Act: -0.0000

Data Index: 1239887 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.1323. Min Act: -0.0000

Data Index: 1800616 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.3917. Min Act: -0.0000

Data Index: 925669 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1476971 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 3.9418. Min Range: -3.9418

Max Act: 2.9182. Min Act: -0.0000

Data Index: 1091744 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.3556. Min Act: -0.0000

Data Index: 931809 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.0514. Min Act: -0.0000

Data Index: 1851379 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.3582. Min Act: -0.0000

Data Index: 1496378 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.1656. Min Act: -0.0000

Data Index: 314746 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.0523. Min Act: -0.0000

Data Index: 638852 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 3.9418. Min Range: -3.9418

Max Act: 3.0236. Min Act: -0.0000

Data Index: 846780 (The Pile)

Max Activating Token Index: 591