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

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

Neuron 1996 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3165. Min Act: -0.0001

Data Index: 795394 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3318. Min Act: -0.0001

Data Index: 195124 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3049. Min Act: -0.0001

Data Index: 673611 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3020. Min Act: -0.0001

Data Index: 110974 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3412. Min Act: -0.0001

Data Index: 464281 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3273. Min Act: -0.0001

Data Index: 298837 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2917. Min Act: -0.0001

Data Index: 907219 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3111. Min Act: -0.0001

Data Index: 456533 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2954. Min Act: -0.0001

Data Index: 386042 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2830. Min Act: -0.0001

Data Index: 664238 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2814. Min Act: -0.0001

Data Index: 184700 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.3085. Min Act: -0.0001

Data Index: 914694 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2744. Min Act: -0.0001

Data Index: 254531 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1173299 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2897. Min Act: -0.0001

Data Index: 191194 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2664. Min Act: -0.0001

Data Index: 357285 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2507. Min Act: -0.0001

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2748. Min Act: -0.0001

Data Index: 72890 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2663. Min Act: -0.0001

Data Index: 986347 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.3412. Min Range: -0.3412

Max Act: 0.2383. Min Act: -0.0001

Data Index: 369320 (C4 (Web Text))

Max Activating Token Index: 950