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

Dataset: The Pile

Neuron 2526 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: 1.2734. Min Range: -1.2734

Max Act: 1.2734. Min Act: -0.0000

Data Index: 849390 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1314654 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.2734. Min Range: -1.2734

Max Act: 1.0358. Min Act: -0.0000

Data Index: 91842 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1362614 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1939660 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.9302. Min Act: -0.0000

Data Index: 790933 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1458906 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1002940 (The Pile)

Max Activating Token Index: 456

Text #8

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.6332. Min Act: -0.0000

Data Index: 842784 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7488. Min Act: -0.0000

Data Index: 408408 (The Pile)

Max Activating Token Index: 434

Text #10

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1952856 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1937233 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7548. Min Act: -0.0000

Data Index: 981981 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1694654 (The Pile)

Max Activating Token Index: 800

Text #14

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1557783 (The Pile)

Max Activating Token Index: 724

Text #15

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1558743 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1937255 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1487864 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7171. Min Act: -0.0000

Data Index: 851476 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 1.2734. Min Range: -1.2734

Max Act: 0.7295. Min Act: -0.0000

Data Index: 329954 (The Pile)

Max Activating Token Index: 1014