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

Dataset: The Pile

Neuron 93 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: 1.4568. Min Range: -1.4568

Max Act: 1.4568. Min Act: -0.0000

Data Index: 946611 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1996339 (The Pile)

Max Activating Token Index: 25

Text #2

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.3753. Min Act: -0.0000

Data Index: 1100400 (The Pile)

Max Activating Token Index: 691

Text #3

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2036. Min Act: -0.0000

Data Index: 102135 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2692. Min Act: -0.0000

Data Index: 52734 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1697. Min Act: -0.0000

Data Index: 940502 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1870. Min Act: -0.0000

Data Index: 485818 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1004571 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1393. Min Act: -0.0000

Data Index: 186220 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2445. Min Act: -0.0000

Data Index: 651782 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1028503 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1873364 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1154765 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1277. Min Act: -0.0000

Data Index: 881456 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1585. Min Act: -0.0000

Data Index: 924429 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1005779 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1592. Min Act: -0.0000

Data Index: 115251 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1169230 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1454730 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 1.4568. Min Range: -1.4568

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1122264 (The Pile)

Max Activating Token Index: 17