Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1076 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0002

Data Index: 229756 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0550. Min Act: -0.0002

Data Index: 530629 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0528. Min Act: -0.0002

Data Index: 603519 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1214306 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0520. Min Act: -0.0002

Data Index: 582533 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0536. Min Act: -0.0002

Data Index: 59896 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0544. Min Act: -0.0002

Data Index: 483824 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0518. Min Act: -0.0002

Data Index: 97473 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1188858 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0521. Min Act: -0.0002

Data Index: 79970 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0530. Min Act: -0.0002

Data Index: 631923 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0470. Min Act: -0.0002

Data Index: 389399 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0486. Min Act: -0.0002

Data Index: 621420 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0508. Min Act: -0.0002

Data Index: 428657 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1071031 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0513. Min Act: -0.0002

Data Index: 571890 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0518. Min Act: -0.0002

Data Index: 254618 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0513. Min Act: -0.0002

Data Index: 157956 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0508. Min Act: -0.0002

Data Index: 857675 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0502. Min Act: -0.0002

Data Index: 331139 (C4 (Web Text))

Max Activating Token Index: 816