Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6439. Min Range: -1.6439

Max Act: 1.6439. Min Act: -0.0001

Data Index: 746065 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.6439. Min Range: -1.6439

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1028965 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.8543. Min Act: -0.0000

Data Index: 714744 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.8803. Min Act: -0.0000

Data Index: 108095 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.5641. Min Act: -0.0001

Data Index: 781586 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1113382 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.4230. Min Act: -0.0001

Data Index: 334000 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1429197 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.2072. Min Act: -0.0000

Data Index: 296728 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1756. Min Act: -0.0000

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1824. Min Act: -0.0000

Data Index: 779602 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1070001 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1241603 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1219552 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1205700 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1474. Min Act: -0.0001

Data Index: 737986 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1844. Min Act: -0.0000

Data Index: 677544 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1110779 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1622. Min Act: -0.0000

Data Index: 713823 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.6439. Min Range: -1.6439

Max Act: 0.1454. Min Act: -0.0001

Data Index: 134325 (C4 (Web Text))

Max Activating Token Index: 877