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

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

Neuron 5091 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0599. Min Range: -1.0599

Max Act: 1.0599. Min Act: -0.0001

Data Index: 664168 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.0599. Min Range: -1.0599

Max Act: 1.0173. Min Act: -0.0001

Data Index: 1314444 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9542. Min Act: -0.0001

Data Index: 857431 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.9050. Min Act: -0.0001

Data Index: 165617 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8807. Min Act: -0.0001

Data Index: 478566 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8779. Min Act: -0.0001

Data Index: 37779 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8782. Min Act: -0.0002

Data Index: 985187 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8945. Min Act: -0.0001

Data Index: 1228676 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8744. Min Act: -0.0001

Data Index: 217074 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8611. Min Act: -0.0002

Data Index: 355416 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8501. Min Act: -0.0001

Data Index: 1343850 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8631. Min Act: -0.0001

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8740. Min Act: -0.0001

Data Index: 983711 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8451. Min Act: -0.0001

Data Index: 1042738 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8577. Min Act: -0.0001

Data Index: 1189663 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8391. Min Act: -0.0002

Data Index: 1348322 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8571. Min Act: -0.0001

Data Index: 293089 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1319167 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8511. Min Act: -0.0001

Data Index: 1287799 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.0599. Min Range: -1.0599

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1091805 (C4 (Web Text))

Max Activating Token Index: 23