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

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

Neuron 5016 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3207. Min Range: -2.3207

Max Act: 2.3207. Min Act: -0.0000

Data Index: 1633732 (Python Code)

Max Activating Token Index: 451

Text #1

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.2680. Min Act: -0.0000

Data Index: 1631782 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1641267 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.2474. Min Act: -0.0000

Data Index: 1511535 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1480975 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.2092. Min Act: -0.0000

Data Index: 1474681 (Python Code)

Max Activating Token Index: 461

Text #6

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1510121 (Python Code)

Max Activating Token Index: 938

Text #7

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.1444. Min Act: -0.0000

Data Index: 1485592 (Python Code)

Max Activating Token Index: 51

Text #8

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1501742 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1501136 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.9834. Min Act: -0.0000

Data Index: 500829 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1522716 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1386473 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1559352 (Python Code)

Max Activating Token Index: 744

Text #14

Max Range: 2.3207. Min Range: -2.3207

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1585032 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1384146 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1444541 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1016139 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1423743 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 2.3207. Min Range: -2.3207

Max Act: 0.7610. Min Act: -0.0000

Data Index: 1637971 (Python Code)

Max Activating Token Index: 833