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

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

Neuron 1900 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0858. Min Range: -1.0858

Max Act: 1.0790. Min Act: -0.0000

Data Index: 134386 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.0858. Min Range: -1.0858

Max Act: 1.0858. Min Act: -0.0000

Data Index: 209802 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.0858. Min Range: -1.0858

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1044854 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.0858. Min Range: -1.0858

Max Act: 1.0454. Min Act: -0.0000

Data Index: 960322 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.9242. Min Act: -0.0000

Data Index: 635484 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.9025. Min Act: -0.0000

Data Index: 622816 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1222686 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.8443. Min Act: -0.0000

Data Index: 387930 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.8582. Min Act: -0.0000

Data Index: 590795 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7859. Min Act: -0.0000

Data Index: 956531 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1155590 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.8277. Min Act: -0.0000

Data Index: 616582 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1013773 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7747. Min Act: -0.0000

Data Index: 849114 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1057947 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7515. Min Act: -0.0000

Data Index: 984386 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7444. Min Act: -0.0000

Data Index: 960004 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7335. Min Act: -0.0000

Data Index: 849835 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1131229 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.0858. Min Range: -1.0858

Max Act: 0.7569. Min Act: -0.0000

Data Index: 133510 (C4 (Web Text))

Max Activating Token Index: 72