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

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

Neuron 5513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0375. Min Range: -2.0375

Max Act: 2.0375. Min Act: -0.0000

Data Index: 835127 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.9104. Min Act: -0.0000

Data Index: 922891 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 2.0375. Min Range: -2.0375

Max Act: 2.0157. Min Act: -0.0000

Data Index: 175551 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.5913. Min Act: -0.0000

Data Index: 406595 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.4795. Min Act: -0.0000

Data Index: 796126 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1170956 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.2799. Min Act: -0.0000

Data Index: 818474 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1151830 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.3520. Min Act: -0.0000

Data Index: 393975 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1213055 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.2686. Min Act: -0.0000

Data Index: 1219524 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1107555 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1352768 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0168. Min Act: -0.0000

Data Index: 602298 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0707. Min Act: -0.0000

Data Index: 617167 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0666. Min Act: -0.0000

Data Index: 877048 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.1301. Min Act: -0.0000

Data Index: 698454 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0522. Min Act: -0.0000

Data Index: 916128 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0616. Min Act: -0.0000

Data Index: 124216 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 2.0375. Min Range: -2.0375

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1307521 (C4 (Web Text))

Max Activating Token Index: 449