Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1941 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.9977. Min Act: -0.0000

Data Index: 700053 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.9976. Min Act: -0.0001

Data Index: 430211 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.8127. Min Act: -0.0000

Data Index: 516895 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.7704. Min Act: -0.0000

Data Index: 1291698 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6914. Min Act: -0.0000

Data Index: 264534 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.7842. Min Act: -0.0001

Data Index: 355907 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6783. Min Act: -0.0001

Data Index: 852044 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.7300. Min Act: -0.0001

Data Index: 98076 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.7081. Min Act: -0.0001

Data Index: 1117134 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6887. Min Act: -0.0001

Data Index: 222445 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6292. Min Act: -0.0001

Data Index: 1002438 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6207. Min Act: -0.0001

Data Index: 1002394 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6184. Min Act: -0.0001

Data Index: 588132 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.7275. Min Act: -0.0000

Data Index: 1101800 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.6472. Min Act: -0.0000

Data Index: 400306 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.5344. Min Act: -0.0001

Data Index: 1023274 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.5175. Min Act: -0.0000

Data Index: 215560 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.5285. Min Act: -0.0000

Data Index: 690549 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.4977. Min Act: -0.0000

Data Index: 555315 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.9977. Min Range: -1.9977

Max Act: 1.4680. Min Act: -0.0001

Data Index: 1080498 (C4 (Web Text))

Max Activating Token Index: 509