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

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

Neuron 2395 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3878. Min Act: -0.0000

Data Index: 606136 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3774. Min Act: -0.0000

Data Index: 378266 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3658. Min Act: -0.0001

Data Index: 462388 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3486. Min Act: -0.0000

Data Index: 713127 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3577. Min Act: -0.0001

Data Index: 447876 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3360. Min Act: -0.0000

Data Index: 483475 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3312. Min Act: -0.0000

Data Index: 576293 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3433. Min Act: -0.0001

Data Index: 715076 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3254. Min Act: -0.0000

Data Index: 461351 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3051. Min Act: -0.0000

Data Index: 648885 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1006382 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1272257 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3281. Min Act: -0.0000

Data Index: 59902 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3022. Min Act: -0.0000

Data Index: 449355 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3074. Min Act: -0.0000

Data Index: 126633 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3112. Min Act: -0.0001

Data Index: 194918 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3104. Min Act: -0.0000

Data Index: 304100 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.3081. Min Act: -0.0000

Data Index: 667413 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2965. Min Act: -0.0000

Data Index: 551797 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.3878. Min Range: -0.3878

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1330581 (C4 (Web Text))

Max Activating Token Index: 533