Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5654 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2069. Min Range: -1.2069

Max Act: 1.0681. Min Act: -0.0000

Data Index: 665005 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.2069. Min Range: -1.2069

Max Act: 1.2069. Min Act: -0.0000

Data Index: 72352 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9966. Min Act: -0.0000

Data Index: 357458 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1299124 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1337752 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7902. Min Act: -0.0000

Data Index: 59963 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7612. Min Act: -0.0000

Data Index: 650665 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.8443. Min Act: -0.0000

Data Index: 240498 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7134. Min Act: -0.0000

Data Index: 189506 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6441. Min Act: -0.0000

Data Index: 988650 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7139. Min Act: -0.0000

Data Index: 751310 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1305009 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6882. Min Act: -0.0000

Data Index: 870762 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1293536 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6575. Min Act: -0.0000

Data Index: 275603 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.5936. Min Act: -0.0000

Data Index: 138357 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1060524 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6981. Min Act: -0.0000

Data Index: 267539 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6596. Min Act: -0.0000

Data Index: 700386 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.2069. Min Range: -1.2069

Max Act: 0.6351. Min Act: -0.0000

Data Index: 3572 (C4 (Web Text))

Max Activating Token Index: 60