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

Dataset: The Pile

Neuron 509 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: 0.0000

Data Index: 1669989 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0434. Min Act: 0.0000

Data Index: 1658688 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0422. Min Act: 0.0000

Data Index: 1682121 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0416. Min Act: 0.0000

Data Index: 1260208 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0418. Min Act: 0.0000

Data Index: 534938 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0416. Min Act: 0.0000

Data Index: 859371 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0405. Min Act: 0.0000

Data Index: 978435 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1503363 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: 0.0000

Data Index: 50596 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 484602 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 243149 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1672600 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 941330 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 938481 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1816349 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1677537 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1074431 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1500441 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0402. Min Act: -0.0000

Data Index: 1795637 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0399. Min Act: -0.0000

Data Index: 709819 (The Pile)

Max Activating Token Index: 73