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

Dataset: The Pile

Neuron 3616 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: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1185220 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1995464 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5729. Min Act: -0.0000

Data Index: 964612 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1856739 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1226184 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1265919 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5602. Min Act: 0.0000

Data Index: 578746 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5724. Min Act: 0.0000

Data Index: 1796589 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5497. Min Act: 0.0001

Data Index: 529387 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5530. Min Act: -0.0000

Data Index: 836740 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5407. Min Act: 0.0000

Data Index: 1428256 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1052095 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5146. Min Act: 0.0000

Data Index: 480251 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1654211 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5633. Min Act: 0.0000

Data Index: 1810706 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5099. Min Act: -0.0000

Data Index: 325426 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1974106 (The Pile)

Max Activating Token Index: 124

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1598701 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1637203 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5006. Min Act: -0.0000

Data Index: 754716 (The Pile)

Max Activating Token Index: 550