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

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

Neuron 5551 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1221. Min Range: -2.1221

Max Act: 2.1221. Min Act: -0.0000

Data Index: 1384687 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 2.1221. Min Range: -2.1221

Max Act: 2.0718. Min Act: -0.0000

Data Index: 1642526 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1182757 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 2.1221. Min Range: -2.1221

Max Act: 2.0158. Min Act: -0.0000

Data Index: 964606 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9889. Min Act: -0.0000

Data Index: 118872 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9737. Min Act: -0.0000

Data Index: 1636950 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9761. Min Act: -0.0000

Data Index: 1651004 (Python Code)

Max Activating Token Index: 81

Text #7

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9205. Min Act: -0.0000

Data Index: 606071 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9311. Min Act: -0.0000

Data Index: 365155 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 2.1221. Min Range: -2.1221

Max Act: 2.0379. Min Act: -0.0000

Data Index: 1492673 (Python Code)

Max Activating Token Index: 842

Text #10

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.8961. Min Act: -0.0000

Data Index: 1287599 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9918. Min Act: -0.0000

Data Index: 801018 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.6477. Min Act: -0.0000

Data Index: 1399741 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.8101. Min Act: -0.0000

Data Index: 502156 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1587137 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.9018. Min Act: -0.0000

Data Index: 1616092 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1427646 (Python Code)

Max Activating Token Index: 256

Text #17

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.7323. Min Act: -0.0000

Data Index: 1551585 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.7487. Min Act: -0.0000

Data Index: 1535195 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 2.1221. Min Range: -2.1221

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1396696 (Python Code)

Max Activating Token Index: 344