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

Dataset: The Pile

Neuron 1534 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: 1.0378. Min Range: -1.0378

Max Act: 1.0378. Min Act: -0.0000

Data Index: 147322 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9801. Min Act: -0.0000

Data Index: 680733 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1065281 (The Pile)

Max Activating Token Index: 649

Text #3

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8207. Min Act: -0.0000

Data Index: 120673 (The Pile)

Max Activating Token Index: 186

Text #4

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8552. Min Act: -0.0000

Data Index: 812857 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1414319 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7462. Min Act: -0.0000

Data Index: 901848 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7961. Min Act: -0.0000

Data Index: 438559 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7184. Min Act: -0.0000

Data Index: 585684 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7554. Min Act: -0.0000

Data Index: 240811 (The Pile)

Max Activating Token Index: 30

Text #10

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1752428 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1546246 (The Pile)

Max Activating Token Index: 899

Text #12

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1685721 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7558. Min Act: -0.0000

Data Index: 393914 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6883. Min Act: -0.0000

Data Index: 792282 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1951874 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1017005 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1580118 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6622. Min Act: -0.0000

Data Index: 926063 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.0378. Min Range: -1.0378

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1207793 (The Pile)

Max Activating Token Index: 342