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

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

Neuron 554 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: 3.4692. Min Range: -3.4692

Max Act: 3.3965. Min Act: -0.0000

Data Index: 488603 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.4692. Min Act: -0.0000

Data Index: 99649 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.1268. Min Act: -0.0000

Data Index: 1065673 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.4213. Min Act: -0.0000

Data Index: 1201831 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.0986. Min Act: -0.0000

Data Index: 1025637 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.0642. Min Act: -0.0000

Data Index: 171724 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.1462. Min Act: -0.0000

Data Index: 398621 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.9861. Min Act: -0.0000

Data Index: 1337033 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 3.4692. Min Range: -3.4692

Max Act: 3.1519. Min Act: -0.0000

Data Index: 1296374 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.7991. Min Act: -0.0000

Data Index: 441414 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.7555. Min Act: -0.0000

Data Index: 690589 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.7298. Min Act: -0.0000

Data Index: 1269245 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.9855. Min Act: -0.0000

Data Index: 302823 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.7998. Min Act: -0.0000

Data Index: 54383 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.6611. Min Act: -0.0000

Data Index: 414650 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.7903. Min Act: -0.0000

Data Index: 256585 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.5716. Min Act: -0.0000

Data Index: 107791 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.5762. Min Act: -0.0000

Data Index: 726606 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.7126. Min Act: -0.0000

Data Index: 14083 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 3.4692. Min Range: -3.4692

Max Act: 2.5374. Min Act: -0.0000

Data Index: 1126529 (C4 (Web Text))

Max Activating Token Index: 538