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

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

Neuron 3751 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1006. Min Range: -1.1006

Max Act: 1.1006. Min Act: -0.0001

Data Index: 798337 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.8855. Min Act: -0.0001

Data Index: 1623602 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1318411 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6942. Min Act: -0.0001

Data Index: 993053 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1354796 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1004042 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6527. Min Act: -0.0001

Data Index: 165609 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1448124 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6427. Min Act: -0.0001

Data Index: 796987 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5940. Min Act: -0.0001

Data Index: 1328227 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6406. Min Act: -0.0001

Data Index: 390780 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5928. Min Act: -0.0001

Data Index: 1226691 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6306. Min Act: -0.0001

Data Index: 932464 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5725. Min Act: -0.0001

Data Index: 1056817 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5901. Min Act: -0.0001

Data Index: 1467993 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6318. Min Act: -0.0001

Data Index: 172384 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5946. Min Act: -0.0001

Data Index: 820924 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1204123 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.6267. Min Act: -0.0001

Data Index: 161269 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.1006. Min Range: -1.1006

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1549944 (Python Code)

Max Activating Token Index: 988