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

Dataset: The Pile

Neuron 678 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: 1.3322. Min Range: -1.3322

Max Act: 1.3322. Min Act: -0.0000

Data Index: 169049 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1497827 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1174145 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1054972 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1382. Min Act: -0.0000

Data Index: 211591 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.2799. Min Act: -0.0000

Data Index: 486166 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1005029 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1505975 (The Pile)

Max Activating Token Index: 475

Text #8

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1330. Min Act: -0.0000

Data Index: 528645 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1861309 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1009220 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1335823 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1311364 (The Pile)

Max Activating Token Index: 368

Text #13

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1118. Min Act: -0.0000

Data Index: 851472 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1977603 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1377743 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1203. Min Act: -0.0000

Data Index: 631390 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1257657 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.0897. Min Act: -0.0000

Data Index: 237026 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.3322. Min Range: -1.3322

Max Act: 1.1062. Min Act: -0.0000

Data Index: 585282 (The Pile)

Max Activating Token Index: 201