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

Dataset: The Pile

Neuron 3125 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4042. Min Range: -3.4042

Max Act: 3.3219. Min Act: -0.0000

Data Index: 426068 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.9983. Min Act: -0.0000

Data Index: 994578 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.8087. Min Act: -0.0000

Data Index: 1984892 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.9818. Min Act: -0.0000

Data Index: 1432463 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.5872. Min Act: -0.0000

Data Index: 136127 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.7745. Min Act: -0.0000

Data Index: 1082519 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.6691. Min Act: -0.0000

Data Index: 1797303 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.6267. Min Act: -0.0000

Data Index: 1198943 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.5005. Min Act: -0.0000

Data Index: 1448490 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.7373. Min Act: -0.0000

Data Index: 1313676 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 3.4042. Min Range: -3.4042

Max Act: 3.4042. Min Act: -0.0000

Data Index: 1894140 (The Pile)

Max Activating Token Index: 1001

Text #11

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.3716. Min Act: -0.0000

Data Index: 1082829 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.5005. Min Act: -0.0000

Data Index: 416011 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.5769. Min Act: -0.0000

Data Index: 1973929 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.5778. Min Act: -0.0000

Data Index: 846497 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.1547. Min Act: -0.0000

Data Index: 1817449 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.1980. Min Act: -0.0000

Data Index: 812885 (The Pile)

Max Activating Token Index: 200

Text #17

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.2361. Min Act: -0.0000

Data Index: 451010 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.4795. Min Act: -0.0000

Data Index: 220687 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 3.4042. Min Range: -3.4042

Max Act: 2.4721. Min Act: -0.0000

Data Index: 491431 (The Pile)

Max Activating Token Index: 639