Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1587 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0195. Min Range: -1.0195

Max Act: 1.0195. Min Act: -0.0000

Data Index: 151684 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9744. Min Act: -0.0000

Data Index: 617212 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1116392 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1024750 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8367. Min Act: -0.0000

Data Index: 59897 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1184475 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8488. Min Act: -0.0000

Data Index: 210866 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8159. Min Act: -0.0000

Data Index: 623867 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8372. Min Act: 0.0000

Data Index: 1202557 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7694. Min Act: 0.0000

Data Index: 1233704 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7820. Min Act: -0.0000

Data Index: 861579 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7767. Min Act: -0.0000

Data Index: 344392 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7241. Min Act: 0.0000

Data Index: 1238792 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7901. Min Act: -0.0000

Data Index: 978906 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7613. Min Act: -0.0000

Data Index: 503048 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7439. Min Act: -0.0000

Data Index: 378105 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7550. Min Act: -0.0000

Data Index: 221830 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7363. Min Act: 0.0002

Data Index: 863032 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7266. Min Act: -0.0000

Data Index: 877861 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7430. Min Act: -0.0000

Data Index: 646540 (C4 (Web Text))

Max Activating Token Index: 525