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

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

Neuron 3013 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0078. Min Range: -1.0078

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1222662 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.9187. Min Act: -0.0000

Data Index: 834984 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.9743. Min Act: -0.0000

Data Index: 633913 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1259589 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8744. Min Act: -0.0000

Data Index: 145856 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8955. Min Act: -0.0000

Data Index: 91282 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8951. Min Act: -0.0000

Data Index: 30568 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8713. Min Act: -0.0000

Data Index: 657157 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8575. Min Act: -0.0000

Data Index: 342752 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8417. Min Act: -0.0000

Data Index: 993061 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1276770 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8355. Min Act: -0.0000

Data Index: 577599 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8372. Min Act: -0.0000

Data Index: 143730 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1307708 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.7910. Min Act: -0.0000

Data Index: 824201 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.7924. Min Act: -0.0000

Data Index: 928518 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1305625 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1206428 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.7714. Min Act: -0.0000

Data Index: 649168 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 1.0078. Min Range: -1.0078

Max Act: 0.7670. Min Act: -0.0000

Data Index: 556170 (C4 (Web Text))

Max Activating Token Index: 448