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

Dataset: The Pile

Neuron 2006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.5290. Min Act: -0.0000

Data Index: 560531 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.5179. Min Act: -0.0000

Data Index: 188272 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4653. Min Act: -0.0000

Data Index: 1771725 (The Pile)

Max Activating Token Index: 43

Text #3

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4567. Min Act: -0.0000

Data Index: 1403115 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3768. Min Act: -0.0000

Data Index: 854827 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3650. Min Act: -0.0000

Data Index: 357176 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1843349 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1596863 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.4051. Min Act: -0.0000

Data Index: 746229 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1740088 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2943. Min Act: -0.0000

Data Index: 647181 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1183455 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3528. Min Act: -0.0000

Data Index: 757389 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3464. Min Act: -0.0000

Data Index: 506065 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1012848 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1516177 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.3802. Min Act: -0.0000

Data Index: 54798 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1397029 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2717. Min Act: -0.0000

Data Index: 1400144 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.5290. Min Range: -1.5290

Max Act: 1.2580. Min Act: -0.0000

Data Index: 453692 (The Pile)

Max Activating Token Index: 175