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

Dataset: The Pile

Neuron 2781 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0000

Data Index: 680105 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0351. Min Act: 0.0000

Data Index: 1609560 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0338. Min Act: 0.0000

Data Index: 284448 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0337. Min Act: 0.0001

Data Index: 78102 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1269750 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 649247 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 969022 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 994153 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 84269 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 476741 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 1043230 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 595952 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 428824 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 389694 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 464365 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 977462 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: 0.0000

Data Index: 227795 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 759989 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 982777 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0335. Min Act: -0.0000

Data Index: 492724 (The Pile)

Max Activating Token Index: 1