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

Dataset: The Pile

Neuron 2877 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1755366 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1857. Min Act: -0.0000

Data Index: 909992 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1668333 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1312838 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1512. Min Act: -0.0000

Data Index: 901596 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1170063 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.1619. Min Act: -0.0000

Data Index: 378502 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1861563 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9688. Min Act: -0.0000

Data Index: 988039 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1408586 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1728593 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1373893 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1339954 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0122. Min Act: -0.0000

Data Index: 560803 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0025. Min Act: -0.0000

Data Index: 1474778 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.4311. Min Range: -1.4311

Max Act: 1.0724. Min Act: -0.0000

Data Index: 935992 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1723106 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1611477 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9823. Min Act: -0.0000

Data Index: 227757 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 1.4311. Min Range: -1.4311

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1198545 (The Pile)

Max Activating Token Index: 254