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

Dataset: The Pile

Neuron 2072 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.3403. Min Act: -0.0000

Data Index: 522630 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1731019 (The Pile)

Max Activating Token Index: 863

Text #2

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1354993 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2902. Min Act: -0.0000

Data Index: 276683 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1026901 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2668. Min Act: -0.0000

Data Index: 535106 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1489753 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1025528 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1429033 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1881711 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1137802 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1917127 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1512013 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1622657 (The Pile)

Max Activating Token Index: 889

Text #14

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.1778. Min Act: -0.0000

Data Index: 7456 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.1887. Min Act: -0.0000

Data Index: 665739 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2133. Min Act: -0.0000

Data Index: 303968 (The Pile)

Max Activating Token Index: 278

Text #17

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2204. Min Act: -0.0000

Data Index: 195783 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1387514 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 0.3403. Min Range: -0.3403

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1447028 (The Pile)

Max Activating Token Index: 452