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

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

Neuron 3435 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: 0.3351. Min Range: -0.3351

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1560032 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1470308 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1377846 (Python Code)

Max Activating Token Index: 591

Text #3

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1506519 (Python Code)

Max Activating Token Index: 819

Text #4

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1501947 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1481572 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1544069 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1575755 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3237. Min Act: -0.0001

Data Index: 1441586 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2754. Min Act: -0.0001

Data Index: 1486502 (Python Code)

Max Activating Token Index: 860

Text #10

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1382980 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2949. Min Act: -0.0001

Data Index: 1592904 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1412399 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1441539 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1618876 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1419243 (Python Code)

Max Activating Token Index: 786

Text #16

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1404812 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2700. Min Act: -0.0001

Data Index: 1623671 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1390651 (Python Code)

Max Activating Token Index: 1007

Text #19

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2443. Min Act: -0.0001

Data Index: 1379593 (Python Code)

Max Activating Token Index: 861