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

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

Neuron 3726 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.9316. Min Act: -0.0001

Data Index: 1486234 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8554. Min Act: -0.0001

Data Index: 1400461 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8008. Min Act: -0.0001

Data Index: 1389471 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.8370. Min Act: -0.0001

Data Index: 1503928 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6880. Min Act: -0.0001

Data Index: 1417187 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1477700 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6835. Min Act: -0.0001

Data Index: 1644831 (Python Code)

Max Activating Token Index: 621

Text #7

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1362626 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6842. Min Act: -0.0001

Data Index: 1455706 (Python Code)

Max Activating Token Index: 399

Text #9

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6931. Min Act: -0.0001

Data Index: 586286 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6892. Min Act: -0.0001

Data Index: 1652889 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1614143 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1506420 (Python Code)

Max Activating Token Index: 557

Text #13

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6817. Min Act: -0.0001

Data Index: 1422335 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6080. Min Act: -0.0001

Data Index: 1638667 (Python Code)

Max Activating Token Index: 637

Text #15

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6385. Min Act: -0.0001

Data Index: 1465536 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1524622 (Python Code)

Max Activating Token Index: 688

Text #17

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1521515 (Python Code)

Max Activating Token Index: 36

Text #18

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1555945 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 0.9316. Min Range: -0.9316

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1624339 (Python Code)

Max Activating Token Index: 795