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

Dataset: The Pile

Neuron 4861 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4259. Min Act: -0.0000

Data Index: 144417 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4125. Min Act: -0.0000

Data Index: 344041 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.4040. Min Act: -0.0000

Data Index: 265904 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1286576 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3557. Min Act: -0.0000

Data Index: 60388 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3526. Min Act: -0.0000

Data Index: 258608 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3250. Min Act: 0.0000

Data Index: 1216003 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3540. Min Act: 0.0000

Data Index: 1553171 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1798769 (The Pile)

Max Activating Token Index: 275

Text #9

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3099. Min Act: -0.0000

Data Index: 998915 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1318091 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1468749 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3142. Min Act: -0.0000

Data Index: 968581 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1039311 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3143. Min Act: -0.0000

Data Index: 133790 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3133. Min Act: -0.0000

Data Index: 996737 (The Pile)

Max Activating Token Index: 524

Text #16

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1627172 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.2949. Min Act: 0.0000

Data Index: 746445 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.2872. Min Act: -0.0000

Data Index: 266871 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 0.4259. Min Range: -0.4259

Max Act: 0.3035. Min Act: -0.0000

Data Index: 389789 (The Pile)

Max Activating Token Index: 652