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

Dataset: The Pile

Neuron 3594 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: 1.6993. Min Range: -1.6993

Max Act: 1.6993. Min Act: -0.0000

Data Index: 818709 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.6984. Min Act: -0.0000

Data Index: 1280608 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.6023. Min Act: -0.0000

Data Index: 646178 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1619893 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5990. Min Act: -0.0000

Data Index: 974992 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.6909. Min Act: -0.0000

Data Index: 487038 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5844. Min Act: -0.0000

Data Index: 532546 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1679363 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5364. Min Act: -0.0000

Data Index: 385864 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.6805. Min Act: -0.0000

Data Index: 340642 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1415470 (The Pile)

Max Activating Token Index: 225

Text #11

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.4061. Min Act: -0.0000

Data Index: 81033 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1085127 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.6082. Min Act: -0.0000

Data Index: 723344 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1347327 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5188. Min Act: -0.0000

Data Index: 221135 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1998891 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1055371 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1905641 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.6993. Min Range: -1.6993

Max Act: 1.3385. Min Act: -0.0000

Data Index: 421611 (The Pile)

Max Activating Token Index: 768