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

Dataset: The Pile

Neuron 1584 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.2058. Min Act: 0.0000

Data Index: 826499 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.1697. Min Act: -0.0000

Data Index: 234954 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1469926 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.1061. Min Act: 0.0000

Data Index: 729415 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 1.2058. Min Range: -1.2058

Max Act: 1.0016. Min Act: -0.0000

Data Index: 392167 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1124219 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.9012. Min Act: -0.0000

Data Index: 156160 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8690. Min Act: -0.0000

Data Index: 267316 (The Pile)

Max Activating Token Index: 900

Text #8

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8232. Min Act: -0.0000

Data Index: 1612014 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8450. Min Act: -0.0000

Data Index: 952833 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8567. Min Act: -0.0000

Data Index: 864390 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1064273 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8499. Min Act: -0.0000

Data Index: 410240 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1518886 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1840923 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.6958. Min Act: -0.0000

Data Index: 1809689 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.7619. Min Act: 0.0000

Data Index: 1588973 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.6311. Min Act: -0.0000

Data Index: 703925 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.7382. Min Act: -0.0000

Data Index: 479364 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 1.2058. Min Range: -1.2058

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1270040 (The Pile)

Max Activating Token Index: 301