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

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

Neuron 380 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: 0.6670. Min Range: -0.6670

Max Act: 0.6670. Min Act: -0.0000

Data Index: 973793 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5841. Min Act: -0.0000

Data Index: 606393 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1265894 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1017340 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4870. Min Act: -0.0000

Data Index: 876565 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.5019. Min Act: -0.0000

Data Index: 482506 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1354897 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4283. Min Act: -0.0000

Data Index: 95300 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4504. Min Act: -0.0000

Data Index: 73569 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4663. Min Act: -0.0000

Data Index: 271421 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1113115 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4633. Min Act: -0.0000

Data Index: 497926 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4487. Min Act: -0.0000

Data Index: 612968 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4376. Min Act: -0.0000

Data Index: 490965 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4452. Min Act: -0.0000

Data Index: 48986 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1146548 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4585. Min Act: -0.0000

Data Index: 848167 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4506. Min Act: -0.0000

Data Index: 64016 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4350. Min Act: -0.0000

Data Index: 449992 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.6670. Min Range: -0.6670

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1281196 (C4 (Web Text))

Max Activating Token Index: 924