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

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

Neuron 480 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1118163 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0665. Min Act: -0.0003

Data Index: 665292 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0673. Min Act: -0.0003

Data Index: 534211 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1355251 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0613. Min Act: -0.0002

Data Index: 629534 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0586. Min Act: -0.0003

Data Index: 579528 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0576. Min Act: -0.0003

Data Index: 60739 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0573. Min Act: -0.0003

Data Index: 364679 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1254570 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0555. Min Act: -0.0003

Data Index: 605527 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0546. Min Act: -0.0003

Data Index: 517226 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0542. Min Act: -0.0003

Data Index: 40024 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0542. Min Act: -0.0003

Data Index: 873523 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0541. Min Act: -0.0003

Data Index: 185417 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0535. Min Act: -0.0003

Data Index: 673677 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0534. Min Act: -0.0003

Data Index: 355410 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1220912 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1199508 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0532. Min Act: -0.0003

Data Index: 540489 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0531. Min Act: -0.0003

Data Index: 481063 (C4 (Web Text))

Max Activating Token Index: 16