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

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

Neuron 100 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: 1.0278. Min Range: -1.0278

Max Act: 1.0278. Min Act: -0.0000

Data Index: 446117 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8614. Min Act: -0.0000

Data Index: 768803 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8872. Min Act: -0.0000

Data Index: 925583 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8428. Min Act: -0.0000

Data Index: 223268 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8163. Min Act: -0.0000

Data Index: 1069966 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7668. Min Act: -0.0000

Data Index: 838881 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7878. Min Act: -0.0001

Data Index: 1150707 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7403. Min Act: -0.0000

Data Index: 616282 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8013. Min Act: -0.0000

Data Index: 722429 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7084. Min Act: -0.0000

Data Index: 868849 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7445. Min Act: -0.0001

Data Index: 1024745 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1104727 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7275. Min Act: -0.0000

Data Index: 404498 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1321098 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7106. Min Act: -0.0000

Data Index: 508873 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1068393 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1082250 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1194270 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1170539 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6284. Min Act: -0.0000

Data Index: 546921 (C4 (Web Text))

Max Activating Token Index: 273