Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4998. Min Act: -0.0000

Data Index: 105276 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4528. Min Act: -0.0000

Data Index: 606219 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4428. Min Act: -0.0000

Data Index: 430095 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4099. Min Act: -0.0000

Data Index: 253330 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1343616 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4323. Min Act: -0.0000

Data Index: 79361 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3965. Min Act: -0.0000

Data Index: 294434 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1194367 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3971. Min Act: -0.0000

Data Index: 593310 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3937. Min Act: -0.0000

Data Index: 912004 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3927. Min Act: -0.0000

Data Index: 599986 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3837. Min Act: -0.0000

Data Index: 251088 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3846. Min Act: -0.0000

Data Index: 490358 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.4109. Min Act: -0.0000

Data Index: 709618 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3920. Min Act: -0.0000

Data Index: 6969 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3871. Min Act: -0.0000

Data Index: 54307 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3584. Min Act: -0.0000

Data Index: 876617 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3795. Min Act: -0.0000

Data Index: 877840 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3664. Min Act: -0.0000

Data Index: 275475 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.4998. Min Range: -0.4998

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1258206 (C4 (Web Text))

Max Activating Token Index: 875