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

Dataset: The Pile

Neuron 867 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: 1.0936. Min Range: -1.0936

Max Act: 1.0936. Min Act: -0.0000

Data Index: 961879 (The Pile)

Max Activating Token Index: 765

Text #1

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9228. Min Act: -0.0000

Data Index: 45443 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9664. Min Act: -0.0000

Data Index: 518697 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1214560 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1082952 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9251. Min Act: -0.0000

Data Index: 162900 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1635843 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9130. Min Act: -0.0000

Data Index: 612865 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8384. Min Act: -0.0000

Data Index: 1991030 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1865319 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.9137. Min Act: -0.0000

Data Index: 1102620 (The Pile)

Max Activating Token Index: 947

Text #11

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1728617 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8771. Min Act: -0.0000

Data Index: 597724 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1590085 (The Pile)

Max Activating Token Index: 989

Text #14

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1971524 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1494602 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.7804. Min Act: -0.0000

Data Index: 431574 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8475. Min Act: -0.0000

Data Index: 845358 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.7935. Min Act: -0.0000

Data Index: 813308 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 1.0936. Min Range: -1.0936

Max Act: 0.8379. Min Act: -0.0000

Data Index: 312253 (The Pile)

Max Activating Token Index: 638