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

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

Neuron 1130 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: 0.5419. Min Range: -0.5419

Max Act: 0.4930. Min Act: -0.0000

Data Index: 753962 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.5419. Min Act: -0.0000

Data Index: 356099 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4877. Min Act: -0.0000

Data Index: 705382 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4803. Min Act: -0.0000

Data Index: 609286 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1296049 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1613209 (Python Code)

Max Activating Token Index: 167

Text #6

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1622040 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4547. Min Act: -0.0000

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1465599 (Python Code)

Max Activating Token Index: 213

Text #9

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1437527 (Python Code)

Max Activating Token Index: 220

Text #10

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4208. Min Act: -0.0000

Data Index: 421320 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4260. Min Act: -0.0000

Data Index: 213625 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4551. Min Act: -0.0000

Data Index: 97563 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1548523 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4299. Min Act: -0.0000

Data Index: 324222 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1562575 (Python Code)

Max Activating Token Index: 939

Text #16

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1442963 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1514730 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1380155 (Python Code)

Max Activating Token Index: 343

Text #19

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.3927. Min Act: -0.0000

Data Index: 161295 (C4 (Web Text))

Max Activating Token Index: 474