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

Dataset: The Pile

Neuron 3709 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: 0.5981. Min Range: -0.5981

Max Act: 0.5981. Min Act: -0.0000

Data Index: 590621 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1554771 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5827. Min Act: -0.0000

Data Index: 521420 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5268. Min Act: -0.0000

Data Index: 39488 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1077078 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5231. Min Act: -0.0000

Data Index: 685429 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5089. Min Act: -0.0000

Data Index: 95914 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4884. Min Act: -0.0000

Data Index: 350486 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1570010 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1003646 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1936139 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1214463 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4334. Min Act: -0.0000

Data Index: 597460 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1935456 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4574. Min Act: -0.0000

Data Index: 970494 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1431511 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4805. Min Act: -0.0000

Data Index: 173840 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4481. Min Act: -0.0000

Data Index: 1483654 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4676. Min Act: -0.0000

Data Index: 457285 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.4716. Min Act: -0.0000

Data Index: 221171 (The Pile)

Max Activating Token Index: 343