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

Dataset: The Pile

Neuron 1096 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4020. Min Act: -0.0000

Data Index: 702925 (The Pile)

Max Activating Token Index: 820

Text #1

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1709786 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4024. Min Act: -0.0000

Data Index: 777417 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4313. Min Act: -0.0000

Data Index: 606740 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3733. Min Act: -0.0000

Data Index: 1432109 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.4073. Min Act: -0.0000

Data Index: 333100 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1899939 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3848. Min Act: -0.0000

Data Index: 259030 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3550. Min Act: -0.0000

Data Index: 557627 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1585310 (The Pile)

Max Activating Token Index: 689

Text #10

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1853262 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1333471 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1137082 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3230. Min Act: -0.0000

Data Index: 796281 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3545. Min Act: -0.0000

Data Index: 647287 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1083149 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3570. Min Act: -0.0000

Data Index: 721568 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1452081 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3332. Min Act: -0.0000

Data Index: 471288 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 0.4313. Min Range: -0.4313

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1217321 (The Pile)

Max Activating Token Index: 247