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

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

Neuron 174 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: 0.0829. Min Range: -0.0829

Max Act: 0.0787. Min Act: -0.0001

Data Index: 241021 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1231953 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0795. Min Act: -0.0001

Data Index: 496351 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0738. Min Act: -0.0000

Data Index: 488885 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1392302 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0664. Min Act: -0.0000

Data Index: 1245740 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0662. Min Act: -0.0001

Data Index: 829466 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0678. Min Act: -0.0001

Data Index: 954024 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0667. Min Act: -0.0000

Data Index: 870834 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1361580 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0642. Min Act: -0.0001

Data Index: 135706 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0638. Min Act: -0.0001

Data Index: 65655 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0604. Min Act: -0.0001

Data Index: 600547 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0608. Min Act: -0.0000

Data Index: 1305523 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0612. Min Act: -0.0000

Data Index: 929250 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1053549 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0583. Min Act: -0.0001

Data Index: 254883 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0612. Min Act: -0.0000

Data Index: 556658 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0586. Min Act: -0.0001

Data Index: 548190 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1053749 (C4 (Web Text))

Max Activating Token Index: 899