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

Dataset: The Pile

Neuron 1326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.1736. Min Act: -0.0000

Data Index: 524369 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.1625. Min Act: -0.0000

Data Index: 445666 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.1155. Min Act: 0.0000

Data Index: 1234342 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9946. Min Act: -0.0000

Data Index: 52560 (The Pile)

Max Activating Token Index: 325

Text #4

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.8510. Min Act: -0.0000

Data Index: 513055 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1419652 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9021. Min Act: -0.0000

Data Index: 673749 (The Pile)

Max Activating Token Index: 577

Text #7

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.7598. Min Act: -0.0000

Data Index: 144483 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1446484 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.7932. Min Act: -0.0000

Data Index: 860657 (The Pile)

Max Activating Token Index: 996

Text #10

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1395122 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.7325. Min Act: 0.0000

Data Index: 657330 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1590529 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6769. Min Act: -0.0000

Data Index: 686627 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6869. Min Act: 0.0000

Data Index: 1706433 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6432. Min Act: 0.0000

Data Index: 416570 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1580617 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1028367 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.6484. Min Act: 0.0000

Data Index: 1870513 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.7260. Min Act: 0.0000

Data Index: 1019243 (The Pile)

Max Activating Token Index: 1021