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

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

Neuron 6033 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: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1275531 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5242. Min Act: -0.0000

Data Index: 696404 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5495. Min Act: -0.0000

Data Index: 156636 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1137755 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5366. Min Act: -0.0000

Data Index: 206805 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5231. Min Act: -0.0000

Data Index: 34659 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5549. Min Act: -0.0000

Data Index: 815453 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5468. Min Act: -0.0000

Data Index: 24290 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5292. Min Act: -0.0000

Data Index: 198892 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5289. Min Act: -0.0000

Data Index: 490903 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5390. Min Act: -0.0000

Data Index: 100108 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4958. Min Act: -0.0000

Data Index: 574261 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4752. Min Act: -0.0000

Data Index: 573033 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1225215 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4862. Min Act: -0.0000

Data Index: 410376 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4847. Min Act: -0.0000

Data Index: 676022 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5013. Min Act: -0.0000

Data Index: 67113 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1157582 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4773. Min Act: -0.0000

Data Index: 757925 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1139876 (C4 (Web Text))

Max Activating Token Index: 502