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

Dataset: The Pile

Neuron 4577 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1058. Min Range: -1.1058

Max Act: 1.1058. Min Act: -0.0000

Data Index: 426789 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9570. Min Act: -0.0000

Data Index: 471718 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8423. Min Act: -0.0000

Data Index: 663846 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8784. Min Act: -0.0000

Data Index: 40192 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1095468 (The Pile)

Max Activating Token Index: 716

Text #5

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9325. Min Act: -0.0000

Data Index: 353126 (The Pile)

Max Activating Token Index: 231

Text #6

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1992190 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1034649 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1076201 (The Pile)

Max Activating Token Index: 344

Text #9

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7710. Min Act: -0.0000

Data Index: 895723 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1729697 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7647. Min Act: 0.0001

Data Index: 807223 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8392. Min Act: -0.0000

Data Index: 976942 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1174533 (The Pile)

Max Activating Token Index: 889

Text #14

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1537227 (The Pile)

Max Activating Token Index: 933

Text #15

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1078136 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7332. Min Act: -0.0000

Data Index: 493715 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8037. Min Act: -0.0000

Data Index: 898950 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1088248 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1671373 (The Pile)

Max Activating Token Index: 612