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

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

Neuron 513 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6897. Min Act: -0.0001

Data Index: 803633 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5563. Min Act: -0.0001

Data Index: 407824 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5336. Min Act: -0.0001

Data Index: 1055043 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4971. Min Act: -0.0001

Data Index: 714799 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5489. Min Act: -0.0001

Data Index: 316546 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5544. Min Act: -0.0001

Data Index: 624451 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5062. Min Act: -0.0001

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4604. Min Act: -0.0001

Data Index: 671973 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4780. Min Act: -0.0001

Data Index: 665291 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5029. Min Act: -0.0001

Data Index: 33332 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4808. Min Act: -0.0001

Data Index: 1024588 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4516. Min Act: -0.0001

Data Index: 444392 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4640. Min Act: -0.0001

Data Index: 1209571 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4418. Min Act: -0.0001

Data Index: 322776 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4463. Min Act: -0.0001

Data Index: 34330 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4786. Min Act: -0.0001

Data Index: 527913 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4323. Min Act: -0.0001

Data Index: 234012 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4561. Min Act: -0.0001

Data Index: 858709 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4880. Min Act: -0.0001

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4292. Min Act: -0.0001

Data Index: 85834 (C4 (Web Text))

Max Activating Token Index: 223