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

Dataset: The Pile

Neuron 2860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1506. Min Range: -1.1506

Max Act: 1.1506. Min Act: -0.0000

Data Index: 990930 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 1.1506. Min Range: -1.1506

Max Act: 1.1190. Min Act: -0.0000

Data Index: 550638 (The Pile)

Max Activating Token Index: 681

Text #2

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9708. Min Act: -0.0000

Data Index: 780190 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 1.1506. Min Range: -1.1506

Max Act: 1.0925. Min Act: -0.0000

Data Index: 955303 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1157012 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 1.1506. Min Range: -1.1506

Max Act: 1.0349. Min Act: -0.0000

Data Index: 193854 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1168621 (The Pile)

Max Activating Token Index: 10

Text #7

Max Range: 1.1506. Min Range: -1.1506

Max Act: 1.0211. Min Act: -0.0000

Data Index: 672844 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9524. Min Act: -0.0000

Data Index: 679182 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1516963 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1216039 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9248. Min Act: -0.0000

Data Index: 1794102 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1883622 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1680490 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1615413 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9320. Min Act: -0.0000

Data Index: 745636 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9353. Min Act: -0.0000

Data Index: 12303 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.9229. Min Act: -0.0000

Data Index: 240519 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.8914. Min Act: -0.0000

Data Index: 233050 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1587474 (The Pile)

Max Activating Token Index: 16