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

Dataset: The Pile

Neuron 2512 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: 1.3059. Min Range: -1.3059

Max Act: 1.3059. Min Act: -0.0000

Data Index: 194773 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.2293. Min Act: -0.0000

Data Index: 294294 (The Pile)

Max Activating Token Index: 585

Text #2

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1890. Min Act: -0.0000

Data Index: 919652 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1047385 (The Pile)

Max Activating Token Index: 202

Text #4

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9691. Min Act: -0.0000

Data Index: 385550 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1035. Min Act: -0.0000

Data Index: 116503 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1041737 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0537. Min Act: -0.0000

Data Index: 107073 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1429392 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1437013 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1696231 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1502430 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0856. Min Act: -0.0000

Data Index: 238055 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0852. Min Act: -0.0000

Data Index: 974022 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0944. Min Act: -0.0000

Data Index: 291765 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1066014 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 1.3059. Min Range: -1.3059

Max Act: 1.0484. Min Act: -0.0000

Data Index: 99885 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1567141 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9588. Min Act: -0.0000

Data Index: 292043 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 1.3059. Min Range: -1.3059

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1158507 (The Pile)

Max Activating Token Index: 1016