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

Dataset: The Pile

Neuron 3263 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: 1.7767. Min Range: -1.7767

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1362878 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.5387. Min Act: -0.0000

Data Index: 273583 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4535. Min Act: -0.0000

Data Index: 463934 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.3978. Min Act: -0.0000

Data Index: 14294 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4283. Min Act: -0.0000

Data Index: 50310 (The Pile)

Max Activating Token Index: 153

Text #5

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4217. Min Act: -0.0000

Data Index: 273880 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1014738 (The Pile)

Max Activating Token Index: 248

Text #7

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4879. Min Act: -0.0000

Data Index: 334746 (The Pile)

Max Activating Token Index: 482

Text #8

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1018875 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4334. Min Act: -0.0000

Data Index: 1965059 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1653629 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4054. Min Act: -0.0000

Data Index: 1781669 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.5113. Min Act: -0.0000

Data Index: 147557 (The Pile)

Max Activating Token Index: 209

Text #13

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1775454 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.3893. Min Act: -0.0000

Data Index: 728863 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4241. Min Act: -0.0000

Data Index: 827662 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.5136. Min Act: -0.0000

Data Index: 1588485 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1912385 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4213. Min Act: -0.0000

Data Index: 70326 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 1.7767. Min Range: -1.7767

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1567313 (The Pile)

Max Activating Token Index: 520