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

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

Neuron 616 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1059514 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1070604 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1267735 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6510. Min Act: -0.0000

Data Index: 573863 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6159. Min Act: -0.0000

Data Index: 248876 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.6064. Min Act: -0.0000

Data Index: 166183 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5237. Min Act: -0.0000

Data Index: 393771 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1221126 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1327874 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1346090 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5454. Min Act: -0.0000

Data Index: 649267 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5221. Min Act: -0.0000

Data Index: 846813 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5219. Min Act: -0.0000

Data Index: 889021 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5026. Min Act: -0.0000

Data Index: 344610 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5136. Min Act: -0.0000

Data Index: 117033 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4934. Min Act: -0.0000

Data Index: 360178 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5263. Min Act: -0.0000

Data Index: 810382 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.5266. Min Act: -0.0000

Data Index: 921468 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1190162 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.6592. Min Range: -0.6592

Max Act: 0.4954. Min Act: -0.0000

Data Index: 528151 (C4 (Web Text))

Max Activating Token Index: 225