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

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

Neuron 4660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0821. Min Range: -2.0821

Max Act: 2.0821. Min Act: -0.0000

Data Index: 938954 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 2.0821. Min Range: -2.0821

Max Act: 2.0324. Min Act: -0.0000

Data Index: 943739 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.9931. Min Act: -0.0000

Data Index: 607766 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.9627. Min Act: -0.0000

Data Index: 59824 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1331161 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.8752. Min Act: -0.0000

Data Index: 562972 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1001659 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.7343. Min Act: -0.0000

Data Index: 426700 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.6964. Min Act: -0.0000

Data Index: 762469 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.6449. Min Act: -0.0000

Data Index: 1040930 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.5868. Min Act: -0.0000

Data Index: 967510 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1145833 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.6641. Min Act: -0.0000

Data Index: 914857 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.5610. Min Act: -0.0000

Data Index: 1189101 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.6120. Min Act: -0.0000

Data Index: 315499 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.8033. Min Act: -0.0000

Data Index: 227183 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.5172. Min Act: -0.0000

Data Index: 1253446 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.4697. Min Act: -0.0000

Data Index: 821648 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.4784. Min Act: -0.0000

Data Index: 609641 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 2.0821. Min Range: -2.0821

Max Act: 1.5971. Min Act: -0.0000

Data Index: 463614 (C4 (Web Text))

Max Activating Token Index: 885