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

Dataset: The Pile

Neuron 4720 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: 4.3012. Min Range: -4.3012

Max Act: 4.3012. Min Act: -0.0000

Data Index: 480244 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.9404. Min Act: -0.0000

Data Index: 414322 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.0042. Min Act: -0.0000

Data Index: 1272662 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.5513. Min Act: -0.0000

Data Index: 70581 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.4190. Min Act: -0.0000

Data Index: 1062843 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2393. Min Act: -0.0000

Data Index: 325616 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.3919. Min Act: -0.0000

Data Index: 1141220 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.4080. Min Act: -0.0000

Data Index: 1249258 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.0707. Min Act: -0.0000

Data Index: 293085 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.3425. Min Act: -0.0000

Data Index: 335817 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.3424. Min Act: -0.0000

Data Index: 879900 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.3066. Min Act: -0.0000

Data Index: 1194871 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.3065. Min Act: -0.0000

Data Index: 1502683 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2811. Min Act: -0.0000

Data Index: 1282441 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.1247. Min Act: -0.0000

Data Index: 381370 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2802. Min Act: -0.0000

Data Index: 1779449 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2640. Min Act: -0.0000

Data Index: 1228648 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2350. Min Act: -0.0000

Data Index: 1869701 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2717. Min Act: -0.0000

Data Index: 814956 (The Pile)

Max Activating Token Index: 652

Text #19

Max Range: 4.3012. Min Range: -4.3012

Max Act: 3.2713. Min Act: -0.0000

Data Index: 1919348 (The Pile)

Max Activating Token Index: 688