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

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

Neuron 757 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8811. Min Act: -0.0000

Data Index: 34452 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8960. Min Act: -0.0001

Data Index: 660717 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8011. Min Act: -0.0000

Data Index: 526053 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6766. Min Act: -0.0000

Data Index: 801518 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6478. Min Act: -0.0001

Data Index: 1269731 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6775. Min Act: -0.0000

Data Index: 761267 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6455. Min Act: -0.0000

Data Index: 721603 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6236. Min Act: -0.0000

Data Index: 423209 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6411. Min Act: -0.0001

Data Index: 1259077 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6094. Min Act: -0.0001

Data Index: 700068 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6245. Min Act: -0.0001

Data Index: 404287 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6143. Min Act: -0.0000

Data Index: 347964 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5805. Min Act: -0.0000

Data Index: 190469 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5892. Min Act: -0.0001

Data Index: 491151 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5895. Min Act: -0.0000

Data Index: 796511 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1284676 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6038. Min Act: -0.0001

Data Index: 106709 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5785. Min Act: -0.0000

Data Index: 313335 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5774. Min Act: -0.0000

Data Index: 517196 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.5492. Min Act: -0.0000

Data Index: 626280 (C4 (Web Text))

Max Activating Token Index: 336