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

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

Neuron 1892 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1299771 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.6638. Min Act: -0.0001

Data Index: 931184 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5968. Min Act: -0.0001

Data Index: 1173147 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5926. Min Act: -0.0001

Data Index: 1242599 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5954. Min Act: -0.0001

Data Index: 886903 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5373. Min Act: -0.0001

Data Index: 1142341 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5094. Min Act: -0.0000

Data Index: 741010 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1265889 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.5102. Min Act: -0.0001

Data Index: 1186101 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1074555 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4670. Min Act: -0.0001

Data Index: 67378 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4866. Min Act: -0.0001

Data Index: 124614 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4455. Min Act: -0.0001

Data Index: 322099 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4714. Min Act: -0.0001

Data Index: 396856 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4401. Min Act: -0.0001

Data Index: 1055233 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4406. Min Act: -0.0001

Data Index: 485500 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4415. Min Act: -0.0001

Data Index: 649542 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1019358 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4198. Min Act: -0.0001

Data Index: 759590 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.7249. Min Range: -0.7249

Max Act: 0.4655. Min Act: -0.0000

Data Index: 972154 (C4 (Web Text))

Max Activating Token Index: 424