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

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

Neuron 982 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: 1.3952. Min Range: -1.3952

Max Act: 1.3952. Min Act: -0.0000

Data Index: 403573 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.7936. Min Act: -0.0000

Data Index: 515841 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.6247. Min Act: -0.0000

Data Index: 694610 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.5615. Min Act: -0.0000

Data Index: 245498 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.5570. Min Act: -0.0000

Data Index: 267290 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.5446. Min Act: -0.0000

Data Index: 668580 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4741. Min Act: -0.0000

Data Index: 905055 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4869. Min Act: -0.0000

Data Index: 970794 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4792. Min Act: -0.0000

Data Index: 784193 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1057585 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4504. Min Act: -0.0000

Data Index: 172832 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1213197 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4533. Min Act: -0.0000

Data Index: 993895 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1204606 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4850. Min Act: -0.0000

Data Index: 252551 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4272. Min Act: -0.0000

Data Index: 491087 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4396. Min Act: -0.0000

Data Index: 615768 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4349. Min Act: -0.0000

Data Index: 515436 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4384. Min Act: -0.0000

Data Index: 668999 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.4476. Min Act: -0.0000

Data Index: 164227 (C4 (Web Text))

Max Activating Token Index: 373