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

Dataset: The Pile

Neuron 3144 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: 0.6610. Min Range: -0.6610

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1254895 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1423823 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1087312 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1670712 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1181711 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5829. Min Act: -0.0000

Data Index: 219459 (The Pile)

Max Activating Token Index: 95

Text #6

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1691292 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4780. Min Act: -0.0000

Data Index: 75846 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5527. Min Act: -0.0000

Data Index: 799790 (The Pile)

Max Activating Token Index: 779

Text #9

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5489. Min Act: -0.0000

Data Index: 523303 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5197. Min Act: -0.0000

Data Index: 464179 (The Pile)

Max Activating Token Index: 77

Text #11

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1038275 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1498148 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5216. Min Act: -0.0000

Data Index: 697715 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1750116 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5143. Min Act: 0.0001

Data Index: 1893174 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1488451 (The Pile)

Max Activating Token Index: 992

Text #17

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5020. Min Act: -0.0000

Data Index: 509478 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4987. Min Act: -0.0000

Data Index: 37684 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5120. Min Act: -0.0000

Data Index: 592111 (The Pile)

Max Activating Token Index: 407