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

Dataset: The Pile

Neuron 1550 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: 0.7949. Min Range: -0.7949

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1525634 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.7242. Min Act: -0.0000

Data Index: 769316 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6379. Min Act: -0.0000

Data Index: 869153 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5986. Min Act: -0.0000

Data Index: 395765 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5475. Min Act: -0.0000

Data Index: 132098 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1195319 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5020. Min Act: -0.0000

Data Index: 717761 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5569. Min Act: -0.0000

Data Index: 234889 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5796. Min Act: -0.0000

Data Index: 875805 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1389342 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1140502 (The Pile)

Max Activating Token Index: 923

Text #11

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5853. Min Act: -0.0000

Data Index: 904995 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5274. Min Act: -0.0000

Data Index: 156896 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1829093 (The Pile)

Max Activating Token Index: 783

Text #14

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.5097. Min Act: -0.0000

Data Index: 229756 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1966944 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1487775 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1541365 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4237. Min Act: 0.0000

Data Index: 1830278 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.7949. Min Range: -0.7949

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1437979 (The Pile)

Max Activating Token Index: 1009