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

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

Neuron 2260 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5637. Min Act: -0.0000

Data Index: 754318 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1088961 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5030. Min Act: -0.0000

Data Index: 920138 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1214034 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4741. Min Act: -0.0000

Data Index: 316421 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4764. Min Act: -0.0000

Data Index: 766740 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4750. Min Act: -0.0000

Data Index: 516844 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1080405 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4457. Min Act: -0.0000

Data Index: 871584 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4609. Min Act: -0.0000

Data Index: 53556 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4408. Min Act: -0.0000

Data Index: 211161 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1143664 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4308. Min Act: -0.0000

Data Index: 56477 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4322. Min Act: -0.0000

Data Index: 609496 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1255932 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4206. Min Act: -0.0000

Data Index: 183227 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1235534 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.3864. Min Act: -0.0000

Data Index: 961147 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4251. Min Act: -0.0000

Data Index: 503295 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1046708 (C4 (Web Text))

Max Activating Token Index: 490