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

Dataset: The Pile

Neuron 2861 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1484905 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1878. Min Act: -0.0000

Data Index: 811789 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1843160 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0553. Min Act: -0.0000

Data Index: 226650 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1327222 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0253. Min Act: -0.0000

Data Index: 630675 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1396638 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9925. Min Act: -0.0000

Data Index: 902358 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0912. Min Act: -0.0000

Data Index: 1628995 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1174571 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1910491 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1595045 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1459327 (The Pile)

Max Activating Token Index: 956

Text #13

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9006. Min Act: -0.0000

Data Index: 880562 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1573295 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9509. Min Act: -0.0000

Data Index: 402008 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8234. Min Act: -0.0000

Data Index: 9455 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9406. Min Act: -0.0000

Data Index: 826473 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1321774 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1005312 (The Pile)

Max Activating Token Index: 200