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

Dataset: The Pile

Neuron 769 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: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0000

Data Index: 423397 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1848354 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1720851 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0959. Min Act: -0.0000

Data Index: 400803 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1273672 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1607158 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1109125 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0949. Min Act: -0.0000

Data Index: 815024 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1008717 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0902. Min Act: -0.0000

Data Index: 559874 (The Pile)

Max Activating Token Index: 103

Text #10

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0902. Min Act: -0.0000

Data Index: 129758 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0853. Min Act: -0.0000

Data Index: 21583 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1696922 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0861. Min Act: -0.0000

Data Index: 1260091 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1600633 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0787. Min Act: -0.0000

Data Index: 570709 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1729781 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1280550 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0795. Min Act: -0.0000

Data Index: 706458 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.0738. Min Act: -0.0000

Data Index: 70788 (The Pile)

Max Activating Token Index: 379