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

Dataset: The Pile

Neuron 3489 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: 0.8188. Min Range: -0.8188

Max Act: 0.8188. Min Act: -0.0000

Data Index: 146507 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7200. Min Act: -0.0000

Data Index: 43759 (The Pile)

Max Activating Token Index: 658

Text #2

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6834. Min Act: -0.0000

Data Index: 552547 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7398. Min Act: -0.0000

Data Index: 280494 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1612321 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1639660 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1300097 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1156155 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6388. Min Act: -0.0000

Data Index: 169327 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1703352 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1544227 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1482326 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1193945 (The Pile)

Max Activating Token Index: 769

Text #13

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1249070 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6339. Min Act: -0.0000

Data Index: 756136 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5961. Min Act: -0.0000

Data Index: 661522 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5944. Min Act: -0.0000

Data Index: 434459 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1350895 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5542. Min Act: -0.0000

Data Index: 649668 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6931. Min Act: -0.0000

Data Index: 924149 (The Pile)

Max Activating Token Index: 71