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

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

Neuron 2864 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: 0.9048. Min Range: -0.9048

Max Act: 0.9048. Min Act: -0.0001

Data Index: 265428 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.9031. Min Act: -0.0001

Data Index: 1558773 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.8060. Min Act: -0.0001

Data Index: 542833 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.8158. Min Act: -0.0001

Data Index: 460942 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.7837. Min Act: -0.0001

Data Index: 348876 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.7756. Min Act: -0.0001

Data Index: 314499 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.7739. Min Act: -0.0001

Data Index: 607284 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.7380. Min Act: -0.0001

Data Index: 1315755 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6713. Min Act: -0.0001

Data Index: 737229 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.7585. Min Act: -0.0001

Data Index: 219881 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6868. Min Act: -0.0001

Data Index: 445637 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6975. Min Act: -0.0001

Data Index: 240237 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.7070. Min Act: -0.0001

Data Index: 1267273 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6596. Min Act: -0.0001

Data Index: 1296400 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6988. Min Act: -0.0001

Data Index: 957456 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1129621 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6566. Min Act: -0.0001

Data Index: 833270 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6565. Min Act: -0.0001

Data Index: 510925 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6068. Min Act: -0.0001

Data Index: 1114330 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.9048. Min Range: -0.9048

Max Act: 0.6388. Min Act: -0.0001

Data Index: 247146 (C4 (Web Text))

Max Activating Token Index: 242