Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2585 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1017358 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4667. Min Act: -0.0000

Data Index: 1335139 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5445. Min Act: -0.0000

Data Index: 366802 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5539. Min Act: -0.0000

Data Index: 530468 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1212092 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3899. Min Act: -0.0000

Data Index: 664514 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1318223 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3873. Min Act: -0.0000

Data Index: 640931 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2895. Min Act: -0.0000

Data Index: 712673 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1344731 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.4180. Min Act: -0.0000

Data Index: 736118 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1153588 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3124. Min Act: -0.0000

Data Index: 298905 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.3049. Min Act: -0.0000

Data Index: 405030 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2413. Min Act: -0.0000

Data Index: 604827 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.2414. Min Act: -0.0000

Data Index: 994097 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1585. Min Act: -0.0000

Data Index: 537666 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.0913. Min Act: -0.0000

Data Index: 371070 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1874. Min Act: -0.0000

Data Index: 1050896 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 1.5850. Min Range: -1.5850

Max Act: 1.1286. Min Act: -0.0000

Data Index: 304695 (C4 (Web Text))

Max Activating Token Index: 793