Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5000 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1263623 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9095. Min Act: -0.0000

Data Index: 629661 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9305. Min Act: -0.0000

Data Index: 1124966 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8754. Min Act: -0.0000

Data Index: 474366 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1266257 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8732. Min Act: -0.0000

Data Index: 81133 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1114452 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1094679 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7926. Min Act: -0.0000

Data Index: 384297 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7623. Min Act: -0.0000

Data Index: 967432 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8094. Min Act: -0.0000

Data Index: 161315 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7512. Min Act: -0.0000

Data Index: 982799 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7432. Min Act: -0.0000

Data Index: 778437 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.8040. Min Act: -0.0000

Data Index: 413128 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7407. Min Act: -0.0000

Data Index: 973821 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7537. Min Act: -0.0000

Data Index: 300395 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7270. Min Act: -0.0000

Data Index: 214407 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7338. Min Act: -0.0000

Data Index: 448487 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7145. Min Act: -0.0000

Data Index: 859463 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.9716. Min Range: -0.9716

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1040040 (C4 (Web Text))

Max Activating Token Index: 122