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

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

Neuron 1480 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: 2.5177. Min Range: -2.5177

Max Act: 2.5177. Min Act: -0.0000

Data Index: 941109 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 2.5177. Min Range: -2.5177

Max Act: 2.3490. Min Act: -0.0000

Data Index: 1278475 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.5177. Min Range: -2.5177

Max Act: 2.3483. Min Act: -0.0000

Data Index: 559950 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 2.5177. Min Range: -2.5177

Max Act: 2.0331. Min Act: -0.0000

Data Index: 246507 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.9552. Min Act: -0.0000

Data Index: 550876 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.9856. Min Act: -0.0000

Data Index: 200053 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6438. Min Act: -0.0000

Data Index: 1640227 (Python Code)

Max Activating Token Index: 96

Text #7

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.8651. Min Act: -0.0000

Data Index: 793019 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6086. Min Act: -0.0000

Data Index: 674540 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.8768. Min Act: -0.0000

Data Index: 1460794 (Python Code)

Max Activating Token Index: 462

Text #10

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.8199. Min Act: -0.0000

Data Index: 581958 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.8257. Min Act: -0.0000

Data Index: 494499 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.7195. Min Act: -0.0000

Data Index: 1485266 (Python Code)

Max Activating Token Index: 207

Text #13

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.5078. Min Act: -0.0000

Data Index: 868806 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.5120. Min Act: -0.0000

Data Index: 236722 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6031. Min Act: -0.0000

Data Index: 949474 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6740. Min Act: -0.0000

Data Index: 871172 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6669. Min Act: -0.0000

Data Index: 1577172 (Python Code)

Max Activating Token Index: 586

Text #18

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6604. Min Act: -0.0000

Data Index: 823280 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 2.5177. Min Range: -2.5177

Max Act: 1.6424. Min Act: -0.0000

Data Index: 278451 (C4 (Web Text))

Max Activating Token Index: 440