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

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

Neuron 639 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0509. Min Act: -0.0002

Data Index: 608463 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0003

Data Index: 863685 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0516. Min Act: -0.0003

Data Index: 462548 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0463. Min Act: -0.0002

Data Index: 468375 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0435. Min Act: -0.0002

Data Index: 298869 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0414. Min Act: -0.0003

Data Index: 977760 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1009405 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0390. Min Act: -0.0003

Data Index: 471133 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0412. Min Act: -0.0003

Data Index: 432013 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0400. Min Act: -0.0003

Data Index: 949663 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0396. Min Act: -0.0003

Data Index: 1158082 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1208118 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0420. Min Act: -0.0003

Data Index: 845166 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0380. Min Act: -0.0003

Data Index: 900376 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0364. Min Act: -0.0003

Data Index: 1109843 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1309789 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0390. Min Act: -0.0003

Data Index: 771683 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1061471 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0387. Min Act: -0.0003

Data Index: 77802 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1107713 (C4 (Web Text))

Max Activating Token Index: 623