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

Dataset: The Pile

Neuron 4272 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: 1.2616. Min Range: -1.2616

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1687061 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8710. Min Act: -0.0000

Data Index: 422552 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1941780 (The Pile)

Max Activating Token Index: 166

Text #3

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1887232 (The Pile)

Max Activating Token Index: 180

Text #4

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1008272 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1218966 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9758. Min Act: -0.0000

Data Index: 534586 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8203. Min Act: -0.0000

Data Index: 479077 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1496820 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7703. Min Act: -0.0000

Data Index: 31571 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1622792 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7230. Min Act: -0.0000

Data Index: 897907 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1611679 (The Pile)

Max Activating Token Index: 753

Text #13

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7115. Min Act: -0.0000

Data Index: 449326 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1143118 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.6715. Min Act: -0.0000

Data Index: 780919 (The Pile)

Max Activating Token Index: 979

Text #16

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7271. Min Act: -0.0000

Data Index: 490110 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7762. Min Act: -0.0000

Data Index: 925729 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7347. Min Act: -0.0000

Data Index: 551196 (The Pile)

Max Activating Token Index: 11

Text #19

Max Range: 1.2616. Min Range: -1.2616

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1592807 (The Pile)

Max Activating Token Index: 796