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

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

Neuron 2819 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: 1.2865. Min Range: -1.2865

Max Act: 1.2865. Min Act: -0.0000

Data Index: 156135 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0682. Min Act: -0.0000

Data Index: 891961 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9315. Min Act: 0.0000

Data Index: 389969 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9184. Min Act: 0.0001

Data Index: 1308846 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8961. Min Act: -0.0000

Data Index: 367801 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9235. Min Act: -0.0000

Data Index: 7107 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8399. Min Act: -0.0000

Data Index: 309243 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8421. Min Act: 0.0000

Data Index: 162416 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8507. Min Act: -0.0000

Data Index: 436411 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7855. Min Act: 0.0001

Data Index: 83746 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1350146 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8037. Min Act: 0.0000

Data Index: 658845 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8006. Min Act: 0.0000

Data Index: 1109433 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7990. Min Act: -0.0000

Data Index: 666462 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8010. Min Act: 0.0000

Data Index: 310129 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7847. Min Act: -0.0000

Data Index: 404052 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7561. Min Act: -0.0000

Data Index: 170530 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7558. Min Act: 0.0000

Data Index: 563362 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7740. Min Act: -0.0000

Data Index: 843515 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7648. Min Act: -0.0000

Data Index: 555339 (C4 (Web Text))

Max Activating Token Index: 56