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

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

Neuron 59 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: 0.5886. Min Range: -0.5886

Max Act: 0.5886. Min Act: -0.0000

Data Index: 914391 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5625. Min Act: -0.0000

Data Index: 98682 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5522. Min Act: -0.0000

Data Index: 235529 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1167613 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5288. Min Act: -0.0000

Data Index: 261707 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5473. Min Act: -0.0000

Data Index: 871271 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5444. Min Act: -0.0000

Data Index: 581806 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5221. Min Act: -0.0000

Data Index: 366375 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5218. Min Act: -0.0000

Data Index: 548795 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5524. Min Act: -0.0000

Data Index: 524135 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5147. Min Act: -0.0000

Data Index: 958473 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5139. Min Act: -0.0000

Data Index: 691171 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1042292 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4931. Min Act: -0.0000

Data Index: 740008 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4980. Min Act: -0.0000

Data Index: 537046 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5081. Min Act: -0.0000

Data Index: 94009 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4885. Min Act: -0.0000

Data Index: 190193 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.4915. Min Act: -0.0000

Data Index: 99770 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5056. Min Act: -0.0000

Data Index: 483516 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.5886. Min Range: -0.5886

Max Act: 0.5049. Min Act: -0.0000

Data Index: 254567 (C4 (Web Text))

Max Activating Token Index: 17