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

Dataset: The Pile

Neuron 1678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.7798. Min Act: -0.0000

Data Index: 392361 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.7781. Min Act: -0.0000

Data Index: 828475 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 3.7798. Min Range: -3.7798

Max Act: 3.3989. Min Act: -0.0000

Data Index: 938554 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.5602. Min Act: -0.0000

Data Index: 1473378 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.5750. Min Act: -0.0000

Data Index: 813946 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.2197. Min Act: -0.0000

Data Index: 609169 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.3261. Min Act: -0.0000

Data Index: 1129707 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.5398. Min Act: -0.0000

Data Index: 1556978 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.4165. Min Act: -0.0000

Data Index: 937889 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.2715. Min Act: -0.0000

Data Index: 838516 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.4886. Min Act: -0.0000

Data Index: 1317405 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.2434. Min Act: -0.0000

Data Index: 404489 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.3031. Min Act: -0.0000

Data Index: 1398661 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.2684. Min Act: -0.0000

Data Index: 1671936 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.1133. Min Act: -0.0000

Data Index: 1002459 (The Pile)

Max Activating Token Index: 864

Text #15

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.1992. Min Act: -0.0000

Data Index: 1848339 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.1944. Min Act: -0.0000

Data Index: 630536 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.1102. Min Act: -0.0000

Data Index: 1505750 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.0838. Min Act: -0.0000

Data Index: 823075 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 3.7798. Min Range: -3.7798

Max Act: 2.1797. Min Act: -0.0000

Data Index: 1681702 (The Pile)

Max Activating Token Index: 971