Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2976 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0266. Min Range: -1.0266

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1495189 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9356. Min Act: -0.0001

Data Index: 980731 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9871. Min Act: -0.0000

Data Index: 442614 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9280. Min Act: -0.0000

Data Index: 674372 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9313. Min Act: -0.0000

Data Index: 174091 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1626800 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1158710 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1962979 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1967272 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9481. Min Act: -0.0000

Data Index: 528774 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1699381 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8394. Min Act: -0.0000

Data Index: 202691 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8700. Min Act: -0.0000

Data Index: 149343 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1429954 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8627. Min Act: -0.0001

Data Index: 576624 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8593. Min Act: -0.0000

Data Index: 981579 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1064735 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1810234 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1339232 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 1.0266. Min Range: -1.0266

Max Act: 0.8477. Min Act: -0.0000

Data Index: 936466 (The Pile)

Max Activating Token Index: 3