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

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

Neuron 3802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1957. Min Range: -3.1957

Max Act: 3.1957. Min Act: -0.0000

Data Index: 1567816 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 3.1957. Min Range: -3.1957

Max Act: 3.0821. Min Act: -0.0000

Data Index: 826707 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.1957. Min Range: -3.1957

Max Act: 3.0067. Min Act: -0.0000

Data Index: 717242 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.9328. Min Act: -0.0000

Data Index: 692147 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.9159. Min Act: -0.0000

Data Index: 166006 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.9373. Min Act: -0.0000

Data Index: 1000198 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.8501. Min Act: -0.0000

Data Index: 531871 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.7145. Min Act: -0.0000

Data Index: 40019 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.6676. Min Act: -0.0000

Data Index: 605351 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.8697. Min Act: -0.0000

Data Index: 68387 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.4766. Min Act: -0.0000

Data Index: 401692 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.7318. Min Act: -0.0000

Data Index: 278915 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.4926. Min Act: -0.0000

Data Index: 162489 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.5210. Min Act: -0.0000

Data Index: 960623 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.6019. Min Act: -0.0000

Data Index: 1310778 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.6043. Min Act: -0.0000

Data Index: 266441 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.7266. Min Act: -0.0000

Data Index: 647572 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.5764. Min Act: -0.0000

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.5581. Min Act: -0.0000

Data Index: 1261294 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 3.1957. Min Range: -3.1957

Max Act: 2.6935. Min Act: -0.0000

Data Index: 139178 (C4 (Web Text))

Max Activating Token Index: 643