Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 147 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8709. Min Act: -0.0001

Data Index: 18490 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8508. Min Act: -0.0001

Data Index: 541043 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.8300. Min Act: -0.0001

Data Index: 340202 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7354. Min Act: -0.0001

Data Index: 134520 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7701. Min Act: -0.0001

Data Index: 944632 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7659. Min Act: -0.0001

Data Index: 799614 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7213. Min Act: -0.0001

Data Index: 114609 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7279. Min Act: -0.0001

Data Index: 175655 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6992. Min Act: -0.0001

Data Index: 1211802 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6716. Min Act: -0.0001

Data Index: 740652 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1303714 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6759. Min Act: -0.0001

Data Index: 223216 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6818. Min Act: -0.0001

Data Index: 882631 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7042. Min Act: -0.0001

Data Index: 820344 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6849. Min Act: -0.0001

Data Index: 1199287 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7103. Min Act: -0.0001

Data Index: 940595 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7339. Min Act: -0.0001

Data Index: 220915 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7037. Min Act: -0.0001

Data Index: 472931 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6373. Min Act: -0.0001

Data Index: 531470 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6850. Min Act: -0.0001

Data Index: 107618 (C4 (Web Text))

Max Activating Token Index: 436