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

Dataset: The Pile

Neuron 4933 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: 1.8970. Min Range: -1.8970

Max Act: 1.8970. Min Act: -0.0000

Data Index: 780548 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.8540. Min Act: -0.0000

Data Index: 124476 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6846. Min Act: -0.0000

Data Index: 1465245 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6575. Min Act: -0.0000

Data Index: 737238 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1571575 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1158484 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6169. Min Act: -0.0000

Data Index: 103534 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1767843 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5042. Min Act: -0.0000

Data Index: 1494153 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.4251. Min Act: -0.0000

Data Index: 99312 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.4909. Min Act: -0.0000

Data Index: 582483 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.4824. Min Act: -0.0000

Data Index: 135622 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1806891 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.3778. Min Act: -0.0000

Data Index: 352522 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.4587. Min Act: -0.0000

Data Index: 822829 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.4494. Min Act: -0.0000

Data Index: 1042529 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1381044 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.5030. Min Act: -0.0000

Data Index: 737034 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.6295. Min Act: -0.0000

Data Index: 200384 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.8970. Min Range: -1.8970

Max Act: 1.3775. Min Act: -0.0000

Data Index: 969077 (The Pile)

Max Activating Token Index: 675