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

Dataset: The Pile

Neuron 428 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0930. Min Act: -0.0000

Data Index: 331550 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0994. Min Act: -0.0000

Data Index: 308652 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1004302 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1948050 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0856. Min Act: -0.0000

Data Index: 553336 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1972516 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1472066 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0792. Min Act: -0.0000

Data Index: 664805 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1067336 (The Pile)

Max Activating Token Index: 226

Text #9

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0854. Min Act: -0.0000

Data Index: 804565 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1517871 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1352984 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0678. Min Act: -0.0000

Data Index: 486158 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0784. Min Act: -0.0000

Data Index: 838687 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1979808 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0707. Min Act: -0.0000

Data Index: 385708 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1327014 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1776520 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1565121 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 0.0994. Min Range: -0.0994

Max Act: 0.0700. Min Act: -0.0000

Data Index: 483967 (The Pile)

Max Activating Token Index: 268