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

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

Neuron 4895 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.5922. Min Act: -0.0000

Data Index: 1541412 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1444525 (Python Code)

Max Activating Token Index: 728

Text #2

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1511584 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1471428 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0886. Min Act: -0.0000

Data Index: 1505468 (Python Code)

Max Activating Token Index: 322

Text #5

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1398344 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 1.5922. Min Range: -1.5922

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1433512 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1378718 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1570568 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1617655 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1361210 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1617469 (Python Code)

Max Activating Token Index: 46

Text #12

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1400096 (Python Code)

Max Activating Token Index: 632

Text #13

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1579864 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1625661 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1477554 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1436310 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1430371 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1381519 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 1.5922. Min Range: -1.5922

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1481290 (Python Code)

Max Activating Token Index: 99