Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1469 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1097737 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1519570 (The Pile)

Max Activating Token Index: 878

Text #2

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1959758 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5531. Min Act: -0.0000

Data Index: 808943 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1496 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4495. Min Act: -0.0000

Data Index: 899057 (The Pile)

Max Activating Token Index: 291

Text #6

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1457733 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4439. Min Act: -0.0000

Data Index: 861201 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4508. Min Act: -0.0000

Data Index: 877838 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4492. Min Act: -0.0000

Data Index: 225792 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1721175 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1019278 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4644. Min Act: -0.0000

Data Index: 552378 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1092131 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1614794 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1335799 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.3698. Min Act: -0.0000

Data Index: 332823 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1601059 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4101. Min Act: -0.0000

Data Index: 320460 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4121. Min Act: -0.0000

Data Index: 745277 (The Pile)

Max Activating Token Index: 575