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

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

Neuron 172 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2733. Min Range: -5.2733

Max Act: 5.2733. Min Act: -0.0000

Data Index: 355915 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.6658. Min Act: -0.0000

Data Index: 588466 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.5994. Min Act: -0.0000

Data Index: 1014929 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.0576. Min Act: -0.0000

Data Index: 595622 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.8496. Min Act: -0.0000

Data Index: 520936 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 5.2733. Min Range: -5.2733

Max Act: 4.0044. Min Act: -0.0000

Data Index: 668331 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.9745. Min Act: -0.0000

Data Index: 990364 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.6249. Min Act: -0.0000

Data Index: 221448 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.7361. Min Act: -0.0000

Data Index: 511479 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.9701. Min Act: -0.0000

Data Index: 450751 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.4272. Min Act: -0.0000

Data Index: 1235036 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.5397. Min Act: -0.0000

Data Index: 302073 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.6654. Min Act: -0.0000

Data Index: 249215 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.2868. Min Act: -0.0000

Data Index: 925653 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.6053. Min Act: -0.0000

Data Index: 587645 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.8882. Min Act: -0.0000

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.1761. Min Act: -0.0000

Data Index: 1195345 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.5905. Min Act: -0.0000

Data Index: 1354388 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 5.2733. Min Range: -5.2733

Max Act: 3.7761. Min Act: -0.0000

Data Index: 784889 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 5.2733. Min Range: -5.2733

Max Act: 2.9781. Min Act: -0.0000

Data Index: 85376 (C4 (Web Text))

Max Activating Token Index: 221