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

Dataset: The Pile

Neuron 2246 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1612864 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7580. Min Act: -0.0000

Data Index: 1425500 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.8121. Min Act: -0.0000

Data Index: 290544 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1151087 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7141. Min Act: -0.0000

Data Index: 273464 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1290651 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1793083 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.5923. Min Act: -0.0000

Data Index: 202864 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6654. Min Act: -0.0000

Data Index: 1272757 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6319. Min Act: -0.0000

Data Index: 885922 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1842708 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1095720 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1471603 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.3255. Min Act: -0.0000

Data Index: 954489 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1341304 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.2840. Min Act: -0.0000

Data Index: 16033 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.1764. Min Act: -0.0000

Data Index: 162846 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.2430. Min Act: -0.0000

Data Index: 1168265 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.2168. Min Act: -0.0000

Data Index: 743246 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.2156. Min Act: -0.0000

Data Index: 651464 (The Pile)

Max Activating Token Index: 737