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

Dataset: The Pile

Neuron 3978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6468. Min Range: -3.6468

Max Act: 3.6468. Min Act: -0.0000

Data Index: 1924998 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 3.6468. Min Range: -3.6468

Max Act: 3.1033. Min Act: -0.0000

Data Index: 670159 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 3.6468. Min Range: -3.6468

Max Act: 2.8474. Min Act: -0.0000

Data Index: 330357 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 3.6468. Min Range: -3.6468

Max Act: 2.9610. Min Act: -0.0000

Data Index: 141129 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 3.6468. Min Range: -3.6468

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1965575 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 3.6468. Min Range: -3.6468

Max Act: 2.1714. Min Act: -0.0000

Data Index: 1509108 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.8844. Min Act: -0.0000

Data Index: 1189208 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.8994. Min Act: -0.0000

Data Index: 569916 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.9926. Min Act: -0.0000

Data Index: 507932 (The Pile)

Max Activating Token Index: 499

Text #9

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.9990. Min Act: -0.0000

Data Index: 83123 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.8671. Min Act: -0.0000

Data Index: 487771 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.9545. Min Act: -0.0000

Data Index: 1236489 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.8154. Min Act: -0.0000

Data Index: 980690 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.9047. Min Act: -0.0000

Data Index: 1571752 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1679795 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.7120. Min Act: -0.0000

Data Index: 1013383 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.9179. Min Act: -0.0000

Data Index: 458408 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.6717. Min Act: -0.0000

Data Index: 324578 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.6802. Min Act: -0.0000

Data Index: 1625137 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 3.6468. Min Range: -3.6468

Max Act: 1.7779. Min Act: -0.0000

Data Index: 243518 (The Pile)

Max Activating Token Index: 555