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

Dataset: The Pile

Neuron 4218 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.7407. Min Act: -0.0000

Data Index: 1001518 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.5472. Min Act: -0.0000

Data Index: 515183 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.2406. Min Act: -0.0000

Data Index: 836949 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.1608. Min Act: -0.0000

Data Index: 1751496 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.3170. Min Act: -0.0000

Data Index: 1646244 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.0194. Min Act: -0.0000

Data Index: 1684466 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.9849. Min Act: -0.0000

Data Index: 499152 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.9821. Min Act: -0.0000

Data Index: 889884 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.9065. Min Act: -0.0000

Data Index: 1199396 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.6243. Min Act: -0.0000

Data Index: 624193 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.2606. Min Act: -0.0000

Data Index: 827500 (The Pile)

Max Activating Token Index: 754

Text #11

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.8516. Min Act: -0.0000

Data Index: 1926184 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.6177. Min Act: -0.0000

Data Index: 1866308 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.6374. Min Act: -0.0000

Data Index: 243389 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.5622. Min Act: -0.0000

Data Index: 661667 (The Pile)

Max Activating Token Index: 673

Text #15

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.7398. Min Act: -0.0000

Data Index: 119167 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 5.7407. Min Range: -5.7407

Max Act: 5.0798. Min Act: -0.0000

Data Index: 187254 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.3704. Min Act: -0.0000

Data Index: 1486481 (The Pile)

Max Activating Token Index: 198

Text #18

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.6683. Min Act: -0.0000

Data Index: 782807 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 5.7407. Min Range: -5.7407

Max Act: 4.5963. Min Act: -0.0000

Data Index: 1647302 (The Pile)

Max Activating Token Index: 91