Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1700665 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0000

Data Index: 346708 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6130. Min Act: -0.0000

Data Index: 964270 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5633. Min Act: -0.0000

Data Index: 169152 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1165498 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5474. Min Act: -0.0000

Data Index: 653898 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5556. Min Act: -0.0000

Data Index: 402479 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1231976 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1774388 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5591. Min Act: -0.0000

Data Index: 21899 (The Pile)

Max Activating Token Index: 427

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5389. Min Act: -0.0000

Data Index: 2017 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1919563 (The Pile)

Max Activating Token Index: 719

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1892409 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1484544 (The Pile)

Max Activating Token Index: 765

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5074. Min Act: -0.0000

Data Index: 618772 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1749089 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1110998 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1282430 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1878751 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5281. Min Act: -0.0000

Data Index: 613288 (The Pile)

Max Activating Token Index: 898