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

Dataset: The Pile

Neuron 69 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.8981. Min Act: -0.0000

Data Index: 16751 (The Pile)

Max Activating Token Index: 971

Text #1

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.6757. Min Act: -0.0000

Data Index: 1169651 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.5412. Min Act: -0.0000

Data Index: 1322153 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.5080. Min Act: -0.0000

Data Index: 14165 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.1610. Min Act: -0.0000

Data Index: 142202 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.1593. Min Act: -0.0000

Data Index: 1254620 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.7023. Min Act: -0.0000

Data Index: 173739 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3597. Min Act: -0.0000

Data Index: 1922874 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3622. Min Act: -0.0000

Data Index: 1402747 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.4621. Min Act: -0.0000

Data Index: 788955 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.7962. Min Act: -0.0000

Data Index: 823142 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.3254. Min Act: -0.0000

Data Index: 486576 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.9415. Min Act: -0.0000

Data Index: 805421 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.2205. Min Act: -0.0000

Data Index: 1150775 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 3.8981. Min Range: -3.8981

Max Act: 3.0114. Min Act: -0.0000

Data Index: 728110 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.7824. Min Act: -0.0000

Data Index: 1988690 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.7305. Min Act: -0.0000

Data Index: 1404225 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.6760. Min Act: -0.0000

Data Index: 1713400 (The Pile)

Max Activating Token Index: 693

Text #18

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.8127. Min Act: -0.0000

Data Index: 1997319 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 3.8981. Min Range: -3.8981

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1891458 (The Pile)

Max Activating Token Index: 632