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

Dataset: The Pile

Neuron 2229 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4839. Min Act: -0.0000

Data Index: 594386 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1051392 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1675674 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1187943 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1148573 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1744696 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1800296 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1697756 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1305261 (The Pile)

Max Activating Token Index: 1014

Text #9

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1890182 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1959524 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1305161 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1162352 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1577269 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3575. Min Act: -0.0000

Data Index: 756859 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3662. Min Act: -0.0000

Data Index: 61091 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3434. Min Act: -0.0000

Data Index: 432939 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3629. Min Act: -0.0000

Data Index: 535897 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1173014 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 0.4839. Min Range: -0.4839

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1429607 (The Pile)

Max Activating Token Index: 69