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

Dataset: The Pile

Neuron 1876 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: 1.8663. Min Range: -1.8663

Max Act: 1.8663. Min Act: -0.0000

Data Index: 1390027 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.8557. Min Act: -0.0000

Data Index: 235003 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.8513. Min Act: -0.0000

Data Index: 996806 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.8428. Min Act: -0.0000

Data Index: 686696 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1370326 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1530908 (The Pile)

Max Activating Token Index: 650

Text #6

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.6879. Min Act: -0.0000

Data Index: 170798 (The Pile)

Max Activating Token Index: 375

Text #7

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7418. Min Act: -0.0000

Data Index: 1486954 (The Pile)

Max Activating Token Index: 601

Text #8

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.8429. Min Act: -0.0000

Data Index: 745433 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7218. Min Act: -0.0000

Data Index: 591348 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.6419. Min Act: -0.0000

Data Index: 1692740 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7409. Min Act: -0.0000

Data Index: 354472 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.6969. Min Act: -0.0000

Data Index: 470261 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.7058. Min Act: -0.0000

Data Index: 594947 (The Pile)

Max Activating Token Index: 321

Text #14

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1239141 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.8019. Min Act: -0.0000

Data Index: 902973 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.6838. Min Act: -0.0000

Data Index: 934601 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1243983 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.5845. Min Act: -0.0000

Data Index: 1598859 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 1.8663. Min Range: -1.8663

Max Act: 1.6118. Min Act: -0.0000

Data Index: 1449276 (The Pile)

Max Activating Token Index: 452