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

Dataset: The Pile

Neuron 4798 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: 1.2945. Min Range: -1.2945

Max Act: 1.2945. Min Act: -0.0000

Data Index: 540770 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1184262 (The Pile)

Max Activating Token Index: 670

Text #2

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1091238 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1196259 (The Pile)

Max Activating Token Index: 611

Text #4

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0046. Min Act: -0.0000

Data Index: 1267302 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1538217 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1686570 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0311. Min Act: -0.0000

Data Index: 272279 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0570. Min Act: -0.0000

Data Index: 798327 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0383. Min Act: -0.0000

Data Index: 681185 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1888966 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1321867 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 1.2945. Min Range: -1.2945

Max Act: 1.0219. Min Act: -0.0000

Data Index: 502388 (The Pile)

Max Activating Token Index: 934

Text #13

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1783016 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1683618 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1888872 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.8999. Min Act: -0.0000

Data Index: 479198 (The Pile)

Max Activating Token Index: 296

Text #17

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1294680 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9397. Min Act: -0.0000

Data Index: 96521 (The Pile)

Max Activating Token Index: 610

Text #19

Max Range: 1.2945. Min Range: -1.2945

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1256158 (The Pile)

Max Activating Token Index: 217