Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1529371 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.3202. Min Act: -0.0000

Data Index: 1321095 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.3543. Min Act: -0.0000

Data Index: 499440 (The Pile)

Max Activating Token Index: 361

Text #3

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.2711. Min Act: -0.0000

Data Index: 692261 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.2325. Min Act: -0.0000

Data Index: 648124 (The Pile)

Max Activating Token Index: 828

Text #5

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1982. Min Act: -0.0000

Data Index: 204070 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1898. Min Act: -0.0000

Data Index: 612369 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0696. Min Act: -0.0000

Data Index: 860735 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1065178 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1469632 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1829636 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1814. Min Act: -0.0000

Data Index: 175362 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1800632 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1494. Min Act: -0.0000

Data Index: 227307 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0981. Min Act: -0.0000

Data Index: 723795 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0876. Min Act: -0.0000

Data Index: 1648320 (The Pile)

Max Activating Token Index: 649

Text #16

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1049. Min Act: -0.0000

Data Index: 193746 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1054432 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0991. Min Act: -0.0000

Data Index: 204424 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 1.4323. Min Range: -1.4323

Max Act: 1.0886. Min Act: -0.0000

Data Index: 559845 (The Pile)

Max Activating Token Index: 556