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

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

Neuron 3770 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.3814. Min Act: -0.0001

Data Index: 511365 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.1774. Min Act: -0.0001

Data Index: 545477 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.0198. Min Act: -0.0001

Data Index: 252106 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.9776. Min Act: -0.0001

Data Index: 1267104 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 1.3814. Min Range: -1.3814

Max Act: 1.0000. Min Act: -0.0001

Data Index: 570719 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.9608. Min Act: -0.0001

Data Index: 358209 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.9679. Min Act: -0.0000

Data Index: 782931 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8984. Min Act: -0.0001

Data Index: 428618 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.9017. Min Act: -0.0001

Data Index: 474205 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8824. Min Act: -0.0001

Data Index: 803492 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8967. Min Act: -0.0001

Data Index: 108051 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8596. Min Act: -0.0001

Data Index: 42365 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8584. Min Act: -0.0000

Data Index: 24842 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.9136. Min Act: -0.0001

Data Index: 1018615 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8773. Min Act: -0.0001

Data Index: 160575 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8807. Min Act: -0.0001

Data Index: 35821 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8807. Min Act: -0.0001

Data Index: 710243 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1357508 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1313092 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.3814. Min Range: -1.3814

Max Act: 0.8936. Min Act: -0.0001

Data Index: 1356383 (C4 (Web Text))

Max Activating Token Index: 602