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

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

Neuron 2523 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9845. Min Act: -0.0000

Data Index: 628587 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9111. Min Act: -0.0000

Data Index: 168103 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9148. Min Act: -0.0000

Data Index: 620023 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8592. Min Act: -0.0000

Data Index: 975528 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1212479 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8273. Min Act: -0.0000

Data Index: 463352 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7456. Min Act: -0.0000

Data Index: 894693 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8638. Min Act: -0.0000

Data Index: 1480662 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7917. Min Act: -0.0000

Data Index: 698144 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7201. Min Act: -0.0000

Data Index: 517420 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1441467 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1344644 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6501. Min Act: -0.0000

Data Index: 485359 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6684. Min Act: -0.0000

Data Index: 771068 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6131. Min Act: -0.0000

Data Index: 379286 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6502. Min Act: -0.0000

Data Index: 483007 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6915. Min Act: -0.0000

Data Index: 645611 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6184. Min Act: -0.0000

Data Index: 950716 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6863. Min Act: -0.0000

Data Index: 693409 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1112553 (C4 (Web Text))

Max Activating Token Index: 898