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

Dataset: The Pile

Neuron 2548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.9750. Min Act: -0.0000

Data Index: 1872139 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.8595. Min Act: -0.0000

Data Index: 1242779 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.9767. Min Act: -0.0000

Data Index: 11492 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.7778. Min Act: -0.0000

Data Index: 770576 (The Pile)

Max Activating Token Index: 112

Text #4

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.6044. Min Act: -0.0000

Data Index: 731628 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.2926. Min Act: -0.0000

Data Index: 12844 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.2342. Min Act: -0.0000

Data Index: 749547 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.2159. Min Act: -0.0000

Data Index: 80918 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.1455. Min Act: -0.0000

Data Index: 839831 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.1203. Min Act: -0.0000

Data Index: 401468 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.2397. Min Act: -0.0000

Data Index: 659138 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.0710. Min Act: -0.0000

Data Index: 151869 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.3587. Min Act: -0.0000

Data Index: 1329599 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.3472. Min Act: -0.0000

Data Index: 1009516 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.1988. Min Act: -0.0000

Data Index: 876568 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 3.9767. Min Range: -3.9767

Max Act: 2.8806. Min Act: -0.0000

Data Index: 542818 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 3.9767. Min Range: -3.9767

Max Act: 2.5112. Min Act: -0.0000

Data Index: 1199846 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 3.9767. Min Range: -3.9767

Max Act: 2.8971. Min Act: -0.0000

Data Index: 783657 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 3.9767. Min Range: -3.9767

Max Act: 3.0090. Min Act: -0.0000

Data Index: 797978 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 3.9767. Min Range: -3.9767

Max Act: 2.8306. Min Act: -0.0000

Data Index: 412280 (The Pile)

Max Activating Token Index: 194