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

Dataset: The Pile

Neuron 463 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.6303. Min Act: -0.0000

Data Index: 523434 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1540708 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1755464 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4877. Min Act: -0.0000

Data Index: 237631 (The Pile)

Max Activating Token Index: 916

Text #4

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5059. Min Act: -0.0000

Data Index: 562911 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1033625 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4032. Min Act: -0.0000

Data Index: 777838 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1509508 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4325. Min Act: -0.0000

Data Index: 950813 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3978. Min Act: -0.0000

Data Index: 958311 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4094. Min Act: -0.0000

Data Index: 884076 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1895647 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1907348 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1444267 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1633631 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3862. Min Act: -0.0000

Data Index: 103698 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1134017 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1029351 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1720831 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1635714 (The Pile)

Max Activating Token Index: 303