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

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

Neuron 4409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.6269. Min Act: -0.0001

Data Index: 1433540 (Python Code)

Max Activating Token Index: 775

Text #1

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3337. Min Act: -0.0000

Data Index: 650950 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3344. Min Act: -0.0000

Data Index: 362443 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1298312 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2656. Min Act: -0.0000

Data Index: 568757 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1509. Min Act: -0.0000

Data Index: 988504 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.2766. Min Act: -0.0000

Data Index: 418502 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1832. Min Act: -0.0000

Data Index: 412300 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1690. Min Act: -0.0000

Data Index: 13328 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1594. Min Act: -0.0000

Data Index: 103283 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.1326. Min Act: -0.0000

Data Index: 100329 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0936. Min Act: -0.0000

Data Index: 811105 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0772. Min Act: -0.0000

Data Index: 716017 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0410. Min Act: -0.0000

Data Index: 388976 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.6269. Min Range: -1.6269

Max Act: 0.9905. Min Act: -0.0000

Data Index: 628989 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1076566 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.6269. Min Range: -1.6269

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1138747 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0461. Min Act: -0.0000

Data Index: 460721 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0446. Min Act: -0.0000

Data Index: 837029 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.6269. Min Range: -1.6269

Max Act: 1.0450. Min Act: -0.0000

Data Index: 661937 (C4 (Web Text))

Max Activating Token Index: 888