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

Dataset: The Pile

Neuron 4143 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: 0.3990. Min Range: -0.3990

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1073988 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3784. Min Act: -0.0000

Data Index: 648811 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1129592 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2779. Min Act: -0.0000

Data Index: 141921 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2854. Min Act: -0.0000

Data Index: 872621 (The Pile)

Max Activating Token Index: 548

Text #5

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1694991 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2662. Min Act: -0.0000

Data Index: 91405 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2721. Min Act: -0.0000

Data Index: 440190 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1262065 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1918060 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2479. Min Act: -0.0000

Data Index: 81118 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2372. Min Act: -0.0000

Data Index: 952244 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2517. Min Act: -0.0000

Data Index: 865576 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2432. Min Act: -0.0000

Data Index: 825001 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1770955 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1969082 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1762104 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2263. Min Act: -0.0000

Data Index: 763145 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1796413 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1048010 (The Pile)

Max Activating Token Index: 91