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

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

Neuron 3235 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.6992. Min Act: -0.0001

Data Index: 387580 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.3456. Min Act: -0.0001

Data Index: 704429 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.6992. Min Range: -3.6992

Max Act: 3.0252. Min Act: -0.0001

Data Index: 1130274 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.9136. Min Act: -0.0000

Data Index: 642135 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.6139. Min Act: -0.0001

Data Index: 154495 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.7328. Min Act: -0.0001

Data Index: 67071 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.7860. Min Act: -0.0001

Data Index: 1158191 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.6248. Min Act: -0.0001

Data Index: 1034010 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.4218. Min Act: -0.0001

Data Index: 155985 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.5792. Min Act: -0.0001

Data Index: 874706 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.6865. Min Act: -0.0001

Data Index: 564178 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.2493. Min Act: -0.0000

Data Index: 1124986 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.7064. Min Act: -0.0000

Data Index: 1225591 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.3392. Min Act: -0.0000

Data Index: 424905 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.4300. Min Act: -0.0001

Data Index: 425157 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.2992. Min Act: -0.0001

Data Index: 350377 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 3.6992. Min Range: -3.6992

Max Act: 1.2019. Min Act: -0.0001

Data Index: 618560 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.3209. Min Act: -0.0001

Data Index: 553525 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.4201. Min Act: -0.0001

Data Index: 138502 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 3.6992. Min Range: -3.6992

Max Act: 2.0593. Min Act: -0.0001

Data Index: 414501 (C4 (Web Text))

Max Activating Token Index: 806