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

Dataset: The Pile

Neuron 93 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1901734 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1492565 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2760. Min Act: -0.0000

Data Index: 1983060 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.2378. Min Act: -0.0000

Data Index: 547710 (The Pile)

Max Activating Token Index: 452

Text #4

Max Range: 1.4648. Min Range: -1.4648

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1931174 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9466. Min Act: -0.0000

Data Index: 93155 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8771. Min Act: -0.0000

Data Index: 942606 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1866235 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8930. Min Act: -0.0000

Data Index: 913365 (The Pile)

Max Activating Token Index: 597

Text #9

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1782106 (The Pile)

Max Activating Token Index: 147

Text #10

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8667. Min Act: -0.0000

Data Index: 799548 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8600. Min Act: -0.0000

Data Index: 4171 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8121. Min Act: -0.0000

Data Index: 214782 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1087428 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.7939. Min Act: -0.0000

Data Index: 122797 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1622353 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1402499 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.7460. Min Act: -0.0000

Data Index: 646201 (The Pile)

Max Activating Token Index: 105

Text #18

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.7521. Min Act: -0.0000

Data Index: 571216 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.4648. Min Range: -1.4648

Max Act: 0.7402. Min Act: -0.0000

Data Index: 18352 (The Pile)

Max Activating Token Index: 964