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

Dataset: The Pile

Neuron 3072 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: 1.2331. Min Range: -1.2331

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1205987 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 1.2331. Min Range: -1.2331

Max Act: 1.0445. Min Act: -0.0000

Data Index: 323869 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 1.2331. Min Range: -1.2331

Max Act: 1.0147. Min Act: -0.0000

Data Index: 298890 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 1.2331. Min Range: -1.2331

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1772061 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.9487. Min Act: -0.0000

Data Index: 885749 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1075309 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8803. Min Act: -0.0000

Data Index: 904388 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.9404. Min Act: -0.0000

Data Index: 3626 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.9057. Min Act: -0.0000

Data Index: 149255 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.7553. Min Act: -0.0000

Data Index: 177690 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1690233 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8449. Min Act: -0.0000

Data Index: 144748 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1895254 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8137. Min Act: -0.0000

Data Index: 671814 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1583371 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8002. Min Act: -0.0000

Data Index: 332460 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8769. Min Act: -0.0000

Data Index: 982686 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1480587 (The Pile)

Max Activating Token Index: 907

Text #18

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.8677. Min Act: -0.0000

Data Index: 185742 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 1.2331. Min Range: -1.2331

Max Act: 0.7162. Min Act: -0.0000

Data Index: 657249 (The Pile)

Max Activating Token Index: 186