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

Dataset: The Pile

Neuron 1060 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: 1.8057. Min Range: -1.8057

Max Act: 1.8057. Min Act: -0.0000

Data Index: 466146 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.6336. Min Act: -0.0000

Data Index: 273605 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.5906. Min Act: -0.0000

Data Index: 690489 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.4837. Min Act: -0.0000

Data Index: 67337 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3302. Min Act: -0.0000

Data Index: 1264888 (The Pile)

Max Activating Token Index: 251

Text #5

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1420910 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1251324 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3443. Min Act: -0.0000

Data Index: 69674 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1877729 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.3192. Min Act: -0.0000

Data Index: 565261 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2223. Min Act: -0.0000

Data Index: 343423 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2084. Min Act: -0.0000

Data Index: 544226 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1028740 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1930902 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1212397 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1498385 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.2041. Min Act: -0.0000

Data Index: 283963 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1325439 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1629712 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 1.8057. Min Range: -1.8057

Max Act: 1.1387. Min Act: -0.0000

Data Index: 376529 (The Pile)

Max Activating Token Index: 353