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

Dataset: The Pile

Neuron 2469 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.5637. Min Act: -0.0000

Data Index: 345888 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.0942. Min Act: -0.0000

Data Index: 918271 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.3300. Min Act: -0.0000

Data Index: 470073 (The Pile)

Max Activating Token Index: 148

Text #3

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1089851 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.0034. Min Act: -0.0000

Data Index: 957733 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.0624. Min Act: -0.0000

Data Index: 231006 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.0566. Min Act: -0.0000

Data Index: 559793 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 1.5637. Min Range: -1.5637

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1465149 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.9842. Min Act: -0.0000

Data Index: 448657 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1988143 (The Pile)

Max Activating Token Index: 488

Text #10

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.7382. Min Act: -0.0000

Data Index: 379763 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.9069. Min Act: -0.0000

Data Index: 709893 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1574177 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.9637. Min Act: -0.0000

Data Index: 564685 (The Pile)

Max Activating Token Index: 75

Text #14

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1980831 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1080010 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.7870. Min Act: -0.0000

Data Index: 450334 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.8872. Min Act: -0.0000

Data Index: 587313 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1521818 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 1.5637. Min Range: -1.5637

Max Act: 0.7211. Min Act: -0.0000

Data Index: 215544 (The Pile)

Max Activating Token Index: 164