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

Dataset: The Pile

Neuron 2495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5013. Min Act: -0.0000

Data Index: 407286 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1559641 (The Pile)

Max Activating Token Index: 476

Text #2

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1721302 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1264532 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1764782 (The Pile)

Max Activating Token Index: 138

Text #5

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4813. Min Act: -0.0000

Data Index: 580549 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4167. Min Act: -0.0000

Data Index: 529019 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4305. Min Act: -0.0000

Data Index: 761342 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1320928 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1215366 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1449619 (The Pile)

Max Activating Token Index: 972

Text #11

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4980. Min Act: -0.0000

Data Index: 786045 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4032. Min Act: -0.0000

Data Index: 93230 (The Pile)

Max Activating Token Index: 414

Text #13

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4522. Min Act: -0.0000

Data Index: 191217 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4833. Min Act: -0.0000

Data Index: 697492 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4528. Min Act: -0.0000

Data Index: 264230 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4213. Min Act: -0.0000

Data Index: 955742 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4148. Min Act: -0.0000

Data Index: 726950 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.3762. Min Act: -0.0000

Data Index: 937369 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.6054. Min Range: -0.6054

Max Act: 0.4317. Min Act: -0.0000

Data Index: 865397 (The Pile)

Max Activating Token Index: 537