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

Dataset: The Pile

Neuron 3183 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: 0.5434. Min Range: -0.5434

Max Act: 0.5311. Min Act: -0.0000

Data Index: 99112 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1424862 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1951965 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1537912 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1781294 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1087580 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4534. Min Act: -0.0000

Data Index: 39669 (The Pile)

Max Activating Token Index: 364

Text #7

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1351483 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1450893 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1077140 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4494. Min Act: -0.0000

Data Index: 66715 (The Pile)

Max Activating Token Index: 493

Text #11

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1591316 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1103058 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4264. Min Act: -0.0000

Data Index: 953134 (The Pile)

Max Activating Token Index: 595

Text #14

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4100. Min Act: -0.0000

Data Index: 836232 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1200171 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4303. Min Act: -0.0000

Data Index: 705498 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1586488 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1523199 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.5434. Min Range: -0.5434

Max Act: 0.4206. Min Act: -0.0000

Data Index: 840163 (The Pile)

Max Activating Token Index: 275