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

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

Neuron 2599 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1229550 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0790. Min Act: -0.0000

Data Index: 329939 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0774. Min Act: -0.0001

Data Index: 602817 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0743. Min Act: -0.0001

Data Index: 550987 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0732. Min Act: -0.0000

Data Index: 591535 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0701. Min Act: -0.0001

Data Index: 390995 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0705. Min Act: -0.0001

Data Index: 554737 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0689. Min Act: -0.0000

Data Index: 227051 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0648. Min Act: -0.0001

Data Index: 136978 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1204396 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1324917 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0633. Min Act: -0.0001

Data Index: 277573 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1275543 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0577. Min Act: -0.0000

Data Index: 74558 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0598. Min Act: -0.0001

Data Index: 38236 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0592. Min Act: -0.0001

Data Index: 959574 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0614. Min Act: -0.0000

Data Index: 224599 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0587. Min Act: -0.0000

Data Index: 669688 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0587. Min Act: -0.0001

Data Index: 817525 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0577. Min Act: -0.0001

Data Index: 526065 (C4 (Web Text))

Max Activating Token Index: 966