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

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

Neuron 3304 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: 0.5086. Min Range: -0.5086

Max Act: 0.4930. Min Act: -0.0001

Data Index: 336063 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4921. Min Act: -0.0001

Data Index: 500463 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.5004. Min Act: -0.0001

Data Index: 1403914 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4802. Min Act: -0.0001

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4888. Min Act: -0.0001

Data Index: 1612295 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.5086. Min Act: -0.0001

Data Index: 462474 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4390. Min Act: -0.0001

Data Index: 417227 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4562. Min Act: -0.0001

Data Index: 406847 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3722. Min Act: -0.0001

Data Index: 1653965 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3577. Min Act: -0.0001

Data Index: 89038 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1119895 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3757. Min Act: -0.0001

Data Index: 118914 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3832. Min Act: -0.0001

Data Index: 632946 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1477111 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3911. Min Act: -0.0001

Data Index: 614441 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3693. Min Act: -0.0001

Data Index: 1271556 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3795. Min Act: -0.0001

Data Index: 197764 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3741. Min Act: -0.0001

Data Index: 1327196 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.4007. Min Act: -0.0001

Data Index: 1379863 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.5086. Min Range: -0.5086

Max Act: 0.3593. Min Act: -0.0001

Data Index: 1323899 (C4 (Web Text))

Max Activating Token Index: 131