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

Dataset: The Pile

Neuron 3067 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: 0.6237. Min Range: -0.6237

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1817816 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4914. Min Act: -0.0000

Data Index: 403251 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4438. Min Act: -0.0000

Data Index: 780767 (The Pile)

Max Activating Token Index: 881

Text #3

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4630. Min Act: -0.0000

Data Index: 324517 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1237457 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4289. Min Act: -0.0000

Data Index: 1553336 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1751082 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1053192 (The Pile)

Max Activating Token Index: 1000

Text #8

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4078. Min Act: -0.0000

Data Index: 741079 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4564. Min Act: -0.0000

Data Index: 557331 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1637121 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1431737 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4185. Min Act: -0.0000

Data Index: 910698 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4253. Min Act: -0.0000

Data Index: 245994 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4028. Min Act: -0.0000

Data Index: 840250 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.3548. Min Act: -0.0000

Data Index: 330963 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1287659 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1064496 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1537802 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.6237. Min Range: -0.6237

Max Act: 0.3846. Min Act: -0.0000

Data Index: 934611 (The Pile)

Max Activating Token Index: 775