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

Dataset: The Pile

Neuron 1299 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.9774. Min Act: -0.0000

Data Index: 1568500 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.3128. Min Act: -0.0000

Data Index: 851461 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.1394. Min Act: -0.0000

Data Index: 1355065 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.4217. Min Act: -0.0000

Data Index: 522601 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.4403. Min Act: -0.0000

Data Index: 1041688 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 3.9774. Min Range: -3.9774

Max Act: 3.1826. Min Act: -0.0000

Data Index: 164713 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.9202. Min Act: -0.0000

Data Index: 39410 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.9060. Min Act: -0.0000

Data Index: 349332 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.8453. Min Act: -0.0000

Data Index: 1659589 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.9943. Min Act: -0.0000

Data Index: 528923 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.5551. Min Act: -0.0000

Data Index: 750333 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.9003. Min Act: -0.0000

Data Index: 1450228 (The Pile)

Max Activating Token Index: 211

Text #12

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.9255. Min Act: -0.0001

Data Index: 1252937 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.7888. Min Act: -0.0000

Data Index: 377683 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.9118. Min Act: -0.0000

Data Index: 864723 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.8041. Min Act: -0.0000

Data Index: 1855797 (The Pile)

Max Activating Token Index: 725

Text #16

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.8343. Min Act: -0.0000

Data Index: 199868 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.6867. Min Act: -0.0000

Data Index: 1504991 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.7665. Min Act: -0.0000

Data Index: 1974508 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 3.9774. Min Range: -3.9774

Max Act: 2.8096. Min Act: -0.0000

Data Index: 399329 (The Pile)

Max Activating Token Index: 553