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

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

Neuron 4306 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: 2.3488. Min Range: -2.3488

Max Act: 2.3041. Min Act: -0.0000

Data Index: 45857 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 2.3488. Min Range: -2.3488

Max Act: 2.1703. Min Act: -0.0001

Data Index: 850697 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 2.3488. Min Range: -2.3488

Max Act: 2.1555. Min Act: -0.0001

Data Index: 1204222 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 2.3488. Min Range: -2.3488

Max Act: 2.3488. Min Act: -0.0001

Data Index: 686580 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.9622. Min Act: -0.0000

Data Index: 892127 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.9038. Min Act: -0.0001

Data Index: 678470 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.7353. Min Act: -0.0000

Data Index: 480965 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.8788. Min Act: -0.0000

Data Index: 469064 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.8294. Min Act: -0.0001

Data Index: 967343 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.7126. Min Act: -0.0000

Data Index: 226806 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.6944. Min Act: -0.0001

Data Index: 1162509 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.7871. Min Act: -0.0001

Data Index: 882825 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.5948. Min Act: -0.0001

Data Index: 1188671 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.7972. Min Act: -0.0001

Data Index: 486492 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.7014. Min Act: -0.0000

Data Index: 485661 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.6024. Min Act: -0.0000

Data Index: 410362 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.6865. Min Act: -0.0001

Data Index: 534891 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.6688. Min Act: -0.0000

Data Index: 893566 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.7530. Min Act: -0.0000

Data Index: 580309 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 2.3488. Min Range: -2.3488

Max Act: 1.8719. Min Act: -0.0000

Data Index: 188984 (C4 (Web Text))

Max Activating Token Index: 689