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

Dataset: The Pile

Neuron 4606 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: 1.2909. Min Range: -1.2909

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1183762 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2332. Min Act: -0.0000

Data Index: 615276 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1981865 (The Pile)

Max Activating Token Index: 949

Text #3

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1715. Min Act: -0.0000

Data Index: 54807 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1439. Min Act: -0.0000

Data Index: 625514 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1988. Min Act: -0.0000

Data Index: 850007 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0646. Min Act: -0.0000

Data Index: 548918 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.2409. Min Act: -0.0000

Data Index: 1821239 (The Pile)

Max Activating Token Index: 62

Text #8

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1022596 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1100071 (The Pile)

Max Activating Token Index: 61

Text #10

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1766003 (The Pile)

Max Activating Token Index: 876

Text #11

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1875678 (The Pile)

Max Activating Token Index: 61

Text #12

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1820366 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1356399 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1238426 (The Pile)

Max Activating Token Index: 293

Text #15

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.1310. Min Act: -0.0000

Data Index: 376577 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 1.2909. Min Range: -1.2909

Max Act: 1.0269. Min Act: -0.0000

Data Index: 384854 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1407218 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9757. Min Act: -0.0000

Data Index: 570953 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 1.2909. Min Range: -1.2909

Max Act: 0.9622. Min Act: -0.0000

Data Index: 580615 (The Pile)

Max Activating Token Index: 948