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

Dataset: The Pile

Neuron 71 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: 0.7008. Min Range: -0.7008

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1901782 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4642. Min Act: -0.0000

Data Index: 724526 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1563717 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3957. Min Act: -0.0000

Data Index: 787671 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3772. Min Act: -0.0000

Data Index: 282183 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1885195 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3497. Min Act: -0.0000

Data Index: 125302 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1414613 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3253. Min Act: -0.0000

Data Index: 590222 (The Pile)

Max Activating Token Index: 18

Text #9

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3316. Min Act: -0.0000

Data Index: 569681 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1349840 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3492. Min Act: -0.0001

Data Index: 314249 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3934. Min Act: -0.0000

Data Index: 858431 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1175391 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3336. Min Act: -0.0000

Data Index: 958247 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3577. Min Act: -0.0000

Data Index: 1430973 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3225. Min Act: -0.0000

Data Index: 296896 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1735111 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1344554 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.3357. Min Act: -0.0000

Data Index: 575063 (The Pile)

Max Activating Token Index: 748