Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1020512 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.7693. Min Act: -0.0000

Data Index: 133195 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1400088 (Python Code)

Max Activating Token Index: 671

Text #3

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1324378 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.7140. Min Act: -0.0000

Data Index: 680744 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6588. Min Act: -0.0000

Data Index: 518288 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6356. Min Act: -0.0000

Data Index: 984228 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1480429 (Python Code)

Max Activating Token Index: 274

Text #8

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6368. Min Act: -0.0000

Data Index: 614929 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5692. Min Act: -0.0000

Data Index: 935188 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.7097. Min Act: -0.0000

Data Index: 690685 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1310822 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6706. Min Act: -0.0000

Data Index: 505067 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1018708 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6446. Min Act: -0.0000

Data Index: 704904 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6655. Min Act: -0.0000

Data Index: 229677 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6318. Min Act: -0.0000

Data Index: 776498 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6283. Min Act: -0.0000

Data Index: 137361 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5838. Min Act: -0.0000

Data Index: 90600 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1184948 (C4 (Web Text))

Max Activating Token Index: 808