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

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

Neuron 3569 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.5125. Min Act: -0.0000

Data Index: 167465 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.6376. Min Act: -0.0000

Data Index: 214770 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.5904. Min Act: -0.0000

Data Index: 1096879 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4417. Min Act: -0.0000

Data Index: 617408 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4814. Min Act: -0.0000

Data Index: 105749 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.5212. Min Act: -0.0000

Data Index: 342250 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4753. Min Act: -0.0000

Data Index: 803927 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1121105 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4680. Min Act: -0.0000

Data Index: 505561 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4623. Min Act: -0.0000

Data Index: 545322 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.5588. Min Act: -0.0000

Data Index: 136239 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.5097. Min Act: -0.0000

Data Index: 535873 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1314692 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.3292. Min Act: -0.0000

Data Index: 392233 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.3937. Min Act: -0.0000

Data Index: 70347 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.3256. Min Act: -0.0000

Data Index: 988562 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1041964 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.4404. Min Act: -0.0000

Data Index: 232661 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.3973. Min Act: -0.0000

Data Index: 848638 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.6376. Min Range: -1.6376

Max Act: 1.3865. Min Act: -0.0000

Data Index: 836170 (C4 (Web Text))

Max Activating Token Index: 670