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

Dataset: The Pile

Neuron 2478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.9139. Min Act: -0.0000

Data Index: 984578 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1244305 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5971. Min Act: -0.0000

Data Index: 423262 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5088. Min Act: -0.0000

Data Index: 943162 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5914. Min Act: -0.0000

Data Index: 420354 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4693. Min Act: -0.0000

Data Index: 706767 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4217. Min Act: -0.0000

Data Index: 371822 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4165. Min Act: -0.0000

Data Index: 1257123 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5746. Min Act: -0.0000

Data Index: 920804 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5979. Min Act: -0.0000

Data Index: 1792938 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3799. Min Act: -0.0000

Data Index: 497443 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4568. Min Act: -0.0000

Data Index: 667970 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1133219 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1339468 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1318943 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1717310 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3179. Min Act: -0.0000

Data Index: 925626 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4477. Min Act: -0.0000

Data Index: 169452 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3394. Min Act: -0.0000

Data Index: 395925 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.1803. Min Act: -0.0000

Data Index: 609290 (The Pile)

Max Activating Token Index: 910