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

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

Neuron 2664 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2739. Min Range: -4.2739

Max Act: 4.2739. Min Act: -0.0000

Data Index: 503739 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 4.2739. Min Range: -4.2739

Max Act: 3.6543. Min Act: -0.0000

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 4.2739. Min Range: -4.2739

Max Act: 3.6533. Min Act: -0.0000

Data Index: 230012 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 4.2739. Min Range: -4.2739

Max Act: 3.0711. Min Act: -0.0000

Data Index: 175419 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 4.2739. Min Range: -4.2739

Max Act: 3.1016. Min Act: -0.0000

Data Index: 113509 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 4.2739. Min Range: -4.2739

Max Act: 3.0810. Min Act: -0.0000

Data Index: 729321 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 4.2739. Min Range: -4.2739

Max Act: 3.0386. Min Act: -0.0000

Data Index: 1236574 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.5814. Min Act: -0.0000

Data Index: 517507 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.6168. Min Act: -0.0000

Data Index: 827823 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.6699. Min Act: -0.0000

Data Index: 254019 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.6216. Min Act: -0.0000

Data Index: 66689 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.7162. Min Act: -0.0000

Data Index: 159453 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.6001. Min Act: -0.0000

Data Index: 896060 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.6889. Min Act: -0.0000

Data Index: 1101392 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.5052. Min Act: -0.0000

Data Index: 311884 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.6442. Min Act: -0.0000

Data Index: 646042 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.5691. Min Act: -0.0000

Data Index: 326901 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.3486. Min Act: -0.0000

Data Index: 388658 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.4200. Min Act: -0.0000

Data Index: 1323413 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 4.2739. Min Range: -4.2739

Max Act: 2.3858. Min Act: -0.0000

Data Index: 719756 (C4 (Web Text))

Max Activating Token Index: 994