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

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

Neuron 5918 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: 1.6357. Min Range: -1.6357

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1450324 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.6357. Min Act: -0.0000

Data Index: 1611942 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1552461 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.2163. Min Act: -0.0000

Data Index: 24483 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1529846 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1581413 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.1090. Min Act: -0.0000

Data Index: 1058288 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1052700 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0580. Min Act: -0.0000

Data Index: 12323 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0795. Min Act: -0.0000

Data Index: 852954 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9688. Min Act: -0.0000

Data Index: 641992 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0573. Min Act: -0.0000

Data Index: 37626 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1598866 (Python Code)

Max Activating Token Index: 634

Text #13

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9962. Min Act: -0.0000

Data Index: 449512 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0081. Min Act: -0.0000

Data Index: 794445 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9684. Min Act: -0.0000

Data Index: 66902 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9913. Min Act: -0.0000

Data Index: 717920 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.6357. Min Range: -1.6357

Max Act: 1.0249. Min Act: -0.0000

Data Index: 711180 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1259837 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.6357. Min Range: -1.6357

Max Act: 0.9785. Min Act: -0.0000

Data Index: 426516 (C4 (Web Text))

Max Activating Token Index: 398