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

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

Neuron 3976 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.3000. Min Act: -0.0001

Data Index: 1515087 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2479. Min Act: -0.0001

Data Index: 292024 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2335. Min Act: -0.0001

Data Index: 440699 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1573044 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2388. Min Act: -0.0001

Data Index: 919735 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2581. Min Act: -0.0001

Data Index: 723265 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2522. Min Act: -0.0001

Data Index: 622053 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2001. Min Act: -0.0001

Data Index: 639685 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2364. Min Act: -0.0001

Data Index: 773671 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2258. Min Act: -0.0001

Data Index: 833650 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2486. Min Act: -0.0001

Data Index: 664253 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2697. Min Act: -0.0001

Data Index: 975244 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2099. Min Act: -0.0001

Data Index: 1505856 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2468. Min Act: -0.0001

Data Index: 882050 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2262. Min Act: -0.0001

Data Index: 1286663 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2050. Min Act: -0.0001

Data Index: 331706 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1527314 (Python Code)

Max Activating Token Index: 751

Text #17

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1573728 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2302. Min Act: -0.0001

Data Index: 738889 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.3000. Min Range: -0.3000

Max Act: 0.2217. Min Act: -0.0001

Data Index: 139401 (C4 (Web Text))

Max Activating Token Index: 389