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

Dataset: The Pile

Neuron 3410 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: 3.8510. Min Range: -3.8510

Max Act: 3.8510. Min Act: -0.0000

Data Index: 1953665 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 3.8510. Min Range: -3.8510

Max Act: 3.5083. Min Act: -0.0000

Data Index: 598220 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 3.8510. Min Range: -3.8510

Max Act: 3.0973. Min Act: -0.0000

Data Index: 1038627 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 3.8510. Min Range: -3.8510

Max Act: 3.1860. Min Act: -0.0000

Data Index: 836442 (The Pile)

Max Activating Token Index: 530

Text #4

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.7455. Min Act: -0.0000

Data Index: 1586789 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.8939. Min Act: -0.0000

Data Index: 436982 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.8305. Min Act: -0.0000

Data Index: 1568500 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.8382. Min Act: -0.0000

Data Index: 3114 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 3.8510. Min Range: -3.8510

Max Act: 3.0274. Min Act: -0.0000

Data Index: 2613 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.6970. Min Act: -0.0000

Data Index: 1500868 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.5686. Min Act: -0.0000

Data Index: 1825867 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.6621. Min Act: -0.0000

Data Index: 883014 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.6580. Min Act: -0.0000

Data Index: 1773026 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.5104. Min Act: -0.0000

Data Index: 130745 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.6130. Min Act: -0.0000

Data Index: 957211 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.5501. Min Act: -0.0000

Data Index: 195502 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.5031. Min Act: -0.0000

Data Index: 918153 (The Pile)

Max Activating Token Index: 64

Text #17

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1995040 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.1772. Min Act: -0.0000

Data Index: 1373605 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 3.8510. Min Range: -3.8510

Max Act: 2.2897. Min Act: -0.0000

Data Index: 806041 (The Pile)

Max Activating Token Index: 387