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

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

Neuron 5671 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1422257 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1549963 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8748. Min Act: -0.0000

Data Index: 1496476 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1448108 (Python Code)

Max Activating Token Index: 473

Text #4

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1444653 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1441268 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1444418 (Python Code)

Max Activating Token Index: 497

Text #7

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.8575. Min Act: -0.0000

Data Index: 435776 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7940. Min Act: -0.0000

Data Index: 781244 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1632416 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1427724 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1428946 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.9004. Min Act: -0.0000

Data Index: 449481 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7345. Min Act: -0.0000

Data Index: 454129 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7594. Min Act: -0.0000

Data Index: 268765 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1639002 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1516575 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1389934 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1399808 (Python Code)

Max Activating Token Index: 434

Text #19

Max Range: 0.9004. Min Range: -0.9004

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1607002 (Python Code)

Max Activating Token Index: 504