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

Dataset: The Pile

Neuron 2629 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: 0.6263. Min Range: -0.6263

Max Act: 0.6263. Min Act: -0.0000

Data Index: 913768 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1395250 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1278668 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1790682 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1232593 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5835. Min Act: -0.0000

Data Index: 419181 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5406. Min Act: -0.0000

Data Index: 524912 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5695. Min Act: -0.0000

Data Index: 559337 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5867. Min Act: -0.0000

Data Index: 929474 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1044554 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5397. Min Act: -0.0000

Data Index: 586881 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1658220 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5309. Min Act: -0.0000

Data Index: 501468 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1469021 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5055. Min Act: -0.0000

Data Index: 16339 (The Pile)

Max Activating Token Index: 853

Text #15

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1258232 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4687. Min Act: -0.0000

Data Index: 979335 (The Pile)

Max Activating Token Index: 834

Text #17

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5434. Min Act: -0.0000

Data Index: 145453 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1011425 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.6263. Min Range: -0.6263

Max Act: 0.5220. Min Act: -0.0000

Data Index: 290907 (The Pile)

Max Activating Token Index: 50