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

Dataset: The Pile

Neuron 1726 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: 1.7651. Min Range: -1.7651

Max Act: 1.7651. Min Act: -0.0001

Data Index: 934773 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.6057. Min Act: -0.0000

Data Index: 423241 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1463139 (The Pile)

Max Activating Token Index: 50

Text #3

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3584. Min Act: -0.0000

Data Index: 218583 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1661979 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2505. Min Act: -0.0000

Data Index: 35337 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1599492 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2387. Min Act: -0.0000

Data Index: 249684 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2649. Min Act: -0.0000

Data Index: 1709374 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1553043 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1468741 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1537212 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1108. Min Act: -0.0000

Data Index: 155084 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1360636 (The Pile)

Max Activating Token Index: 135

Text #14

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1538. Min Act: -0.0000

Data Index: 347010 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1631. Min Act: -0.0000

Data Index: 372274 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1557833 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1349368 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1798. Min Act: -0.0000

Data Index: 853950 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1352510 (The Pile)

Max Activating Token Index: 724