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

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

Neuron 578 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: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0002

Data Index: 372996 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1173821 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1134319 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0439. Min Act: -0.0003

Data Index: 876932 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0440. Min Act: -0.0003

Data Index: 194569 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0429. Min Act: -0.0002

Data Index: 303860 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0415. Min Act: -0.0003

Data Index: 945991 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0437. Min Act: -0.0003

Data Index: 329666 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0422. Min Act: -0.0002

Data Index: 221338 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0422. Min Act: -0.0002

Data Index: 850773 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0440. Min Act: -0.0003

Data Index: 596749 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0399. Min Act: -0.0003

Data Index: 228394 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0410. Min Act: -0.0003

Data Index: 996228 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0432. Min Act: -0.0003

Data Index: 572343 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0427. Min Act: -0.0003

Data Index: 12292 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0416. Min Act: -0.0003

Data Index: 587815 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0411. Min Act: -0.0003

Data Index: 285852 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0418. Min Act: -0.0002

Data Index: 701673 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1058622 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0409. Min Act: -0.0002

Data Index: 976044 (C4 (Web Text))

Max Activating Token Index: 822