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

Dataset: The Pile

Neuron 2626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.5059. Min Act: -0.0000

Data Index: 923981 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3954. Min Act: -0.0000

Data Index: 1746192 (The Pile)

Max Activating Token Index: 555

Text #2

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3908. Min Act: -0.0000

Data Index: 341495 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3771. Min Act: -0.0000

Data Index: 329917 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1057522 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1664215 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2607. Min Act: -0.0000

Data Index: 1528756 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3058. Min Act: -0.0000

Data Index: 1653178 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1679947 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2794. Min Act: -0.0000

Data Index: 1395242 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2647. Min Act: -0.0000

Data Index: 405553 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2012. Min Act: -0.0000

Data Index: 1787426 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2659. Min Act: -0.0000

Data Index: 932464 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2596. Min Act: -0.0000

Data Index: 830830 (The Pile)

Max Activating Token Index: 964

Text #14

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2531. Min Act: -0.0000

Data Index: 1564746 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2514. Min Act: -0.0000

Data Index: 553668 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2102. Min Act: -0.0000

Data Index: 666984 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1490. Min Act: -0.0000

Data Index: 611465 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1716337 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.1463. Min Act: -0.0000

Data Index: 1239851 (The Pile)

Max Activating Token Index: 819