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

Dataset: The Pile

Neuron 2028 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.3482. Min Act: -0.0000

Data Index: 670147 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1637089 (The Pile)

Max Activating Token Index: 962

Text #2

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0601. Min Act: -0.0000

Data Index: 934829 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0944. Min Act: -0.0000

Data Index: 314721 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1513598 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 1.3482. Min Range: -1.3482

Max Act: 1.0430. Min Act: -0.0000

Data Index: 938075 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9846. Min Act: -0.0000

Data Index: 604355 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8128. Min Act: -0.0000

Data Index: 1095668 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8260. Min Act: -0.0000

Data Index: 182298 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9063. Min Act: -0.0000

Data Index: 452354 (The Pile)

Max Activating Token Index: 295

Text #10

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1271293 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1385640 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1245755 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1783598 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1686730 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8274. Min Act: -0.0000

Data Index: 453820 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.8216. Min Act: -0.0000

Data Index: 1451167 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.7955. Min Act: -0.0000

Data Index: 266636 (The Pile)

Max Activating Token Index: 80

Text #18

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.7756. Min Act: -0.0000

Data Index: 905559 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 1.3482. Min Range: -1.3482

Max Act: 0.7757. Min Act: -0.0000

Data Index: 165565 (The Pile)

Max Activating Token Index: 248