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

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

Neuron 4214 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: 1.3860. Min Range: -1.3860

Max Act: 1.3279. Min Act: 0.0000

Data Index: 271791 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1149507 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.3822. Min Act: -0.0000

Data Index: 219863 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.3860. Min Act: -0.0000

Data Index: 632723 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.3235. Min Act: -0.0000

Data Index: 547076 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.2993. Min Act: -0.0000

Data Index: 455342 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.3501. Min Act: -0.0000

Data Index: 495054 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.2312. Min Act: -0.0000

Data Index: 657751 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.2899. Min Act: -0.0000

Data Index: 861883 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.2596. Min Act: -0.0000

Data Index: 928586 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1093179 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.1492. Min Act: -0.0000

Data Index: 446673 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.1449. Min Act: -0.0000

Data Index: 625947 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.1719. Min Act: 0.0000

Data Index: 81125 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.1276. Min Act: -0.0000

Data Index: 326857 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.0336. Min Act: -0.0000

Data Index: 624218 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.0908. Min Act: -0.0000

Data Index: 255519 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.1124. Min Act: -0.0000

Data Index: 288629 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.0733. Min Act: -0.0000

Data Index: 824573 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.3860. Min Range: -1.3860

Max Act: 1.0658. Min Act: -0.0000

Data Index: 973952 (C4 (Web Text))

Max Activating Token Index: 16