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

Dataset: The Pile

Neuron 3481 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: 0.4822. Min Range: -0.4822

Max Act: 0.4822. Min Act: -0.0000

Data Index: 119202 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4707. Min Act: -0.0000

Data Index: 557673 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4233. Min Act: -0.0000

Data Index: 617591 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4772. Min Act: -0.0000

Data Index: 445875 (The Pile)

Max Activating Token Index: 143

Text #4

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4353. Min Act: -0.0000

Data Index: 670785 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1034290 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3997. Min Act: -0.0000

Data Index: 717805 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1132359 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4041. Min Act: -0.0000

Data Index: 598944 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3784. Min Act: -0.0000

Data Index: 78413 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3504. Min Act: -0.0000

Data Index: 797148 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1717964 (The Pile)

Max Activating Token Index: 105

Text #12

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1489751 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1407560 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1099603 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1245084 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3312. Min Act: -0.0000

Data Index: 360719 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1316145 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3401. Min Act: -0.0000

Data Index: 933331 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1980945 (The Pile)

Max Activating Token Index: 470