Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1115319 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0853. Min Act: -0.0001

Data Index: 859459 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0803. Min Act: -0.0001

Data Index: 103960 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0641. Min Act: -0.0001

Data Index: 742997 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0651. Min Act: -0.0001

Data Index: 100579 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0597. Min Act: -0.0001

Data Index: 413768 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1061641 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0663. Min Act: -0.0001

Data Index: 698493 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0604. Min Act: -0.0001

Data Index: 437950 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0494. Min Act: -0.0001

Data Index: 789272 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0511. Min Act: -0.0001

Data Index: 461898 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1186885 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1119792 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1226122 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0517. Min Act: -0.0001

Data Index: 1341240 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1291536 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0491. Min Act: -0.0001

Data Index: 487653 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1062691 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0525. Min Act: -0.0001

Data Index: 359318 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.0855. Min Range: -0.0855

Max Act: 0.0414. Min Act: -0.0001

Data Index: 597665 (C4 (Web Text))

Max Activating Token Index: 225