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

Dataset: The Pile

Neuron 2882 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2861. Min Act: -0.0000

Data Index: 834685 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1444630 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.2407. Min Act: -0.0000

Data Index: 435112 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0340. Min Act: -0.0000

Data Index: 504444 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9815. Min Act: -0.0000

Data Index: 150749 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 1.2861. Min Range: -1.2861

Max Act: 1.0193. Min Act: -0.0000

Data Index: 187872 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8973. Min Act: -0.0000

Data Index: 467363 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1861292 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9623. Min Act: -0.0000

Data Index: 54148 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8690. Min Act: -0.0000

Data Index: 860423 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1262976 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1206376 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1981080 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9215. Min Act: -0.0000

Data Index: 921280 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1916900 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1448427 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9257. Min Act: -0.0000

Data Index: 584682 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8833. Min Act: -0.0000

Data Index: 551570 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.8929. Min Act: -0.0000

Data Index: 780361 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 1.2861. Min Range: -1.2861

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1819915 (The Pile)

Max Activating Token Index: 856