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

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

Neuron 1627 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4502. Min Range: -3.4502

Max Act: 3.4502. Min Act: -0.0000

Data Index: 494878 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.9091. Min Act: -0.0000

Data Index: 96533 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.7454. Min Act: -0.0000

Data Index: 1011662 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.5608. Min Act: 0.0001

Data Index: 931785 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.6060. Min Act: -0.0000

Data Index: 55964 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.3674. Min Act: 0.0000

Data Index: 891044 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.1521. Min Act: 0.0000

Data Index: 500375 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.2367. Min Act: -0.0000

Data Index: 453187 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.3056. Min Act: -0.0000

Data Index: 191104 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.1924. Min Act: -0.0000

Data Index: 525460 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.1590. Min Act: -0.0000

Data Index: 955973 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.1063. Min Act: -0.0000

Data Index: 563512 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.9746. Min Act: -0.0000

Data Index: 968066 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.0562. Min Act: -0.0000

Data Index: 129702 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.9418. Min Act: 0.0000

Data Index: 1213737 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 3.4502. Min Range: -3.4502

Max Act: 1.6929. Min Act: -0.0000

Data Index: 268479 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.0262. Min Act: -0.0000

Data Index: 110106 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.0167. Min Act: -0.0000

Data Index: 97891 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.0209. Min Act: -0.0000

Data Index: 320384 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 3.4502. Min Range: -3.4502

Max Act: 2.0887. Min Act: -0.0000

Data Index: 923336 (C4 (Web Text))

Max Activating Token Index: 1013