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

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

Neuron 3515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.8874. Min Act: -0.0000

Data Index: 366131 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.7547. Min Act: -0.0000

Data Index: 436664 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.7852. Min Act: -0.0000

Data Index: 871252 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.4980. Min Act: -0.0000

Data Index: 128001 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.3610. Min Act: -0.0000

Data Index: 486204 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.4276. Min Act: -0.0000

Data Index: 464428 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.5092. Min Act: -0.0000

Data Index: 286664 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.4193. Min Act: -0.0000

Data Index: 242038 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.4170. Min Act: -0.0000

Data Index: 443527 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.3430. Min Act: -0.0000

Data Index: 857503 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.4708. Min Act: -0.0000

Data Index: 327047 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.3176. Min Act: -0.0000

Data Index: 861930 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.3467. Min Act: -0.0000

Data Index: 432237 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.3812. Min Act: -0.0000

Data Index: 853777 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.1930. Min Act: -0.0000

Data Index: 219365 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.2905. Min Act: -0.0000

Data Index: 241124 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1017780 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.2819. Min Act: -0.0000

Data Index: 86450 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.2592. Min Act: -0.0000

Data Index: 767393 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 1.8874. Min Range: -1.8874

Max Act: 1.2525. Min Act: -0.0000

Data Index: 213972 (C4 (Web Text))

Max Activating Token Index: 336