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

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

Neuron 6137 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1214864 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1259213 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1195823 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.8662. Min Act: -0.0000

Data Index: 531723 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.8413. Min Act: -0.0000

Data Index: 163490 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1555970 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.8008. Min Act: -0.0000

Data Index: 98893 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1423362 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7160. Min Act: -0.0000

Data Index: 388493 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1447136 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1236354 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.6631. Min Act: -0.0000

Data Index: 286461 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1418383 (Python Code)

Max Activating Token Index: 950

Text #13

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1298147 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.6682. Min Act: -0.0000

Data Index: 784703 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1626730 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1050825 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7137. Min Act: -0.0000

Data Index: 617633 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.7038. Min Act: -0.0000

Data Index: 715500 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.9604. Min Range: -0.9604

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1551098 (Python Code)

Max Activating Token Index: 852