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

Dataset: The Pile

Neuron 4994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.2041. Min Act: -0.0000

Data Index: 193899 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9579. Min Act: -0.0000

Data Index: 445270 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1150303 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8298. Min Act: -0.0000

Data Index: 76460 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1824099 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1598203 (The Pile)

Max Activating Token Index: 501

Text #6

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1751068 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1443722 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1295412 (The Pile)

Max Activating Token Index: 838

Text #9

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6751. Min Act: -0.0000

Data Index: 726172 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1590162 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6961. Min Act: -0.0000

Data Index: 421706 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6154. Min Act: -0.0000

Data Index: 76366 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6634. Min Act: -0.0000

Data Index: 7667 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1222032 (The Pile)

Max Activating Token Index: 960

Text #15

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6452. Min Act: -0.0000

Data Index: 848656 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1890424 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1857877 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1228684 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.6555. Min Act: -0.0000

Data Index: 639124 (The Pile)

Max Activating Token Index: 111