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

Dataset: The Pile

Neuron 4270 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7304. Min Act: -0.0000

Data Index: 20944 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1078282 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1720020 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6895. Min Act: -0.0000

Data Index: 262051 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6082. Min Act: -0.0000

Data Index: 250742 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6141. Min Act: -0.0000

Data Index: 92714 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5768. Min Act: -0.0000

Data Index: 70992 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6209. Min Act: -0.0001

Data Index: 182681 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5343. Min Act: -0.0000

Data Index: 127283 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5422. Min Act: -0.0000

Data Index: 208001 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1368540 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1819520 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1500173 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4658. Min Act: -0.0000

Data Index: 630305 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1134046 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4920. Min Act: -0.0000

Data Index: 827188 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4699. Min Act: -0.0000

Data Index: 454780 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1177824 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1445210 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4818. Min Act: -0.0000

Data Index: 307784 (The Pile)

Max Activating Token Index: 770