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

Dataset: The Pile

Neuron 1661 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.9060. Min Act: -0.0001

Data Index: 1816178 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1319728 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1316251 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1016961 (The Pile)

Max Activating Token Index: 152

Text #4

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7841. Min Act: -0.0000

Data Index: 787219 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1909729 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7552. Min Act: -0.0000

Data Index: 954234 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7904. Min Act: -0.0000

Data Index: 1606900 (The Pile)

Max Activating Token Index: 998

Text #8

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7438. Min Act: -0.0000

Data Index: 857153 (The Pile)

Max Activating Token Index: 200

Text #9

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7505. Min Act: -0.0000

Data Index: 672440 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7534. Min Act: -0.0000

Data Index: 924216 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7244. Min Act: -0.0000

Data Index: 785701 (The Pile)

Max Activating Token Index: 168

Text #12

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7411. Min Act: -0.0000

Data Index: 1389733 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1186642 (The Pile)

Max Activating Token Index: 212

Text #14

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1291802 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1411948 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1482908 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7220. Min Act: -0.0000

Data Index: 854323 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7214. Min Act: -0.0000

Data Index: 501818 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6557. Min Act: -0.0000

Data Index: 438973 (The Pile)

Max Activating Token Index: 672