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

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

Neuron 3578 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.9271. Min Act: -0.0000

Data Index: 158096 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8627. Min Act: -0.0000

Data Index: 280628 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8366. Min Act: -0.0000

Data Index: 512137 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1351265 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1289337 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1283896 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1328093 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7761. Min Act: -0.0000

Data Index: 251589 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7395. Min Act: -0.0000

Data Index: 522591 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1023974 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7369. Min Act: -0.0000

Data Index: 306591 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1333526 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7023. Min Act: -0.0000

Data Index: 83887 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7920. Min Act: -0.0000

Data Index: 862164 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1030771 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.6887. Min Act: -0.0000

Data Index: 921235 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.6775. Min Act: -0.0000

Data Index: 205777 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.6738. Min Act: -0.0000

Data Index: 385003 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.9271. Min Range: -0.9271

Max Act: 0.6698. Min Act: -0.0000

Data Index: 635041 (C4 (Web Text))

Max Activating Token Index: 106