Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1250. Min Act: -0.0000

Data Index: 461074 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1619960 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1811. Min Act: -0.0000

Data Index: 635522 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0094. Min Act: -0.0000

Data Index: 988484 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1075830 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9215. Min Act: -0.0000

Data Index: 962041 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9293. Min Act: -0.0000

Data Index: 90608 (The Pile)

Max Activating Token Index: 845

Text #7

Max Range: 1.1811. Min Range: -1.1811

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1948246 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1583930 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9976. Min Act: -0.0000

Data Index: 180703 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1451441 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1642252 (The Pile)

Max Activating Token Index: 923

Text #12

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8686. Min Act: -0.0000

Data Index: 781990 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.9514. Min Act: -0.0000

Data Index: 477479 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1857918 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1237338 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8127. Min Act: -0.0000

Data Index: 915203 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1201678 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.7554. Min Act: -0.0000

Data Index: 700484 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 1.1811. Min Range: -1.1811

Max Act: 0.8463. Min Act: -0.0000

Data Index: 407926 (The Pile)

Max Activating Token Index: 688