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

Dataset: The Pile

Neuron 2936 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: 1.2303. Min Range: -1.2303

Max Act: 1.2200. Min Act: -0.0000

Data Index: 615179 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1479607 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1665. Min Act: -0.0000

Data Index: 427370 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1349208 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1122. Min Act: -0.0000

Data Index: 431473 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1647. Min Act: -0.0000

Data Index: 155410 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1783. Min Act: -0.0000

Data Index: 913245 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1029141 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1274541 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1522. Min Act: -0.0000

Data Index: 498258 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0734. Min Act: -0.0000

Data Index: 620677 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1471. Min Act: -0.0000

Data Index: 936198 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1630310 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1856084 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1812296 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0687. Min Act: -0.0000

Data Index: 630609 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.9729. Min Act: -0.0000

Data Index: 675487 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.1000. Min Act: -0.0000

Data Index: 1364652 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.2303. Min Range: -1.2303

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1106130 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 1.2303. Min Range: -1.2303

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1422421 (The Pile)

Max Activating Token Index: 482