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

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

Neuron 3407 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.9959. Min Act: -0.0000

Data Index: 395871 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1396464 (Python Code)

Max Activating Token Index: 629

Text #2

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8637. Min Act: -0.0000

Data Index: 1446836 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1418511 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.9394. Min Act: -0.0000

Data Index: 957234 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1560134 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8756. Min Act: -0.0000

Data Index: 190970 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.9139. Min Act: -0.0000

Data Index: 435292 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.7373. Min Act: -0.0000

Data Index: 1603115 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8512. Min Act: -0.0000

Data Index: 459332 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.7880. Min Act: -0.0000

Data Index: 1450610 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.7329. Min Act: -0.0000

Data Index: 1617001 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8405. Min Act: -0.0000

Data Index: 1328676 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.7996. Min Act: -0.0000

Data Index: 1424574 (Python Code)

Max Activating Token Index: 343

Text #14

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8633. Min Act: -0.0000

Data Index: 1532549 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8615. Min Act: -0.0000

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.7484. Min Act: -0.0000

Data Index: 465835 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8548. Min Act: -0.0000

Data Index: 1531746 (Python Code)

Max Activating Token Index: 1022

Text #18

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.8298. Min Act: -0.0000

Data Index: 1605042 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 1.9959. Min Range: -1.9959

Max Act: 1.7604. Min Act: -0.0000

Data Index: 277733 (C4 (Web Text))

Max Activating Token Index: 870