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

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

Neuron 3004 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2570. Min Range: -3.2570

Max Act: 3.2570. Min Act: -0.0000

Data Index: 1460649 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 3.2570. Min Range: -3.2570

Max Act: 3.2291. Min Act: -0.0000

Data Index: 1454036 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.5706. Min Act: -0.0000

Data Index: 1480411 (Python Code)

Max Activating Token Index: 908

Text #3

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.6546. Min Act: -0.0000

Data Index: 1360488 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.4974. Min Act: -0.0000

Data Index: 1625739 (Python Code)

Max Activating Token Index: 799

Text #5

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.5473. Min Act: -0.0000

Data Index: 811402 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.7100. Min Act: -0.0000

Data Index: 802760 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.5590. Min Act: -0.0000

Data Index: 1641882 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.2924. Min Act: -0.0000

Data Index: 605599 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.3003. Min Act: -0.0000

Data Index: 751522 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.2603. Min Act: -0.0000

Data Index: 1375135 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.3704. Min Act: -0.0000

Data Index: 1624525 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.4992. Min Act: -0.0000

Data Index: 913427 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.1135. Min Act: -0.0000

Data Index: 1541895 (Python Code)

Max Activating Token Index: 346

Text #14

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.4272. Min Act: -0.0000

Data Index: 1496862 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.4312. Min Act: -0.0000

Data Index: 1556402 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.2370. Min Act: -0.0000

Data Index: 1620786 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.1021. Min Act: -0.0000

Data Index: 147220 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.2141. Min Act: -0.0000

Data Index: 1539863 (Python Code)

Max Activating Token Index: 182

Text #19

Max Range: 3.2570. Min Range: -3.2570

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1559980 (Python Code)

Max Activating Token Index: 765