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

Dataset: The Pile

Neuron 1853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1782. Min Range: -2.1782

Max Act: 2.1782. Min Act: -0.0000

Data Index: 145693 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.7915. Min Act: -0.0000

Data Index: 1634917 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.9306. Min Act: -0.0000

Data Index: 1376557 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.8912. Min Act: -0.0000

Data Index: 1143425 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.6495. Min Act: -0.0000

Data Index: 315172 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.8113. Min Act: -0.0000

Data Index: 1120498 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.7153. Min Act: -0.0000

Data Index: 1565094 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.7126. Min Act: -0.0000

Data Index: 430103 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1134036 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.6426. Min Act: -0.0000

Data Index: 1970542 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1832660 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.7381. Min Act: -0.0000

Data Index: 15828 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.6651. Min Act: -0.0000

Data Index: 1520254 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.6380. Min Act: -0.0000

Data Index: 315794 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.7043. Min Act: -0.0000

Data Index: 1315017 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.5105. Min Act: -0.0000

Data Index: 754686 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.5740. Min Act: -0.0000

Data Index: 1132136 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.3941. Min Act: -0.0000

Data Index: 709091 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1621133 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 2.1782. Min Range: -2.1782

Max Act: 1.6158. Min Act: -0.0000

Data Index: 113551 (The Pile)

Max Activating Token Index: 972