Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3010 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0003

Data Index: 383760 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0883. Min Act: -0.0003

Data Index: 1326803 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0813. Min Act: -0.0003

Data Index: 1185299 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0837. Min Act: -0.0003

Data Index: 1308405 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0826. Min Act: -0.0003

Data Index: 20109 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1233478 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0798. Min Act: -0.0003

Data Index: 186227 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0704. Min Act: -0.0003

Data Index: 712233 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0730. Min Act: -0.0003

Data Index: 537163 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0760. Min Act: -0.0003

Data Index: 277425 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0734. Min Act: -0.0003

Data Index: 881507 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0702. Min Act: -0.0003

Data Index: 533369 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0684. Min Act: -0.0003

Data Index: 1163702 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0726. Min Act: -0.0003

Data Index: 666170 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0704. Min Act: -0.0003

Data Index: 292807 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0725. Min Act: -0.0003

Data Index: 650985 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0674. Min Act: -0.0003

Data Index: 928188 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0705. Min Act: -0.0003

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 964