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

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

Neuron 1727 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: 3.1407. Min Range: -3.1407

Max Act: 3.1407. Min Act: -0.0000

Data Index: 1540455 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.5549. Min Act: 0.0000

Data Index: 1447920 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.4391. Min Act: -0.0000

Data Index: 1573966 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.2901. Min Act: -0.0000

Data Index: 1572078 (Python Code)

Max Activating Token Index: 488

Text #4

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.3997. Min Act: 0.0000

Data Index: 1650769 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.2805. Min Act: -0.0000

Data Index: 1575199 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1587289 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.0990. Min Act: -0.0000

Data Index: 1642291 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.2219. Min Act: -0.0000

Data Index: 1456598 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.2095. Min Act: -0.0000

Data Index: 1378447 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1553061 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.2521. Min Act: 0.0000

Data Index: 1430024 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.1257. Min Act: -0.0000

Data Index: 1509445 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 3.1407. Min Range: -3.1407

Max Act: 1.9873. Min Act: 0.0000

Data Index: 1399979 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.0839. Min Act: -0.0000

Data Index: 1423720 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.1811. Min Act: -0.0000

Data Index: 1612024 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.0846. Min Act: -0.0000

Data Index: 1468667 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1641839 (Python Code)

Max Activating Token Index: 739

Text #18

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.0416. Min Act: -0.0000

Data Index: 1470585 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 3.1407. Min Range: -3.1407

Max Act: 2.0451. Min Act: -0.0000

Data Index: 1588990 (Python Code)

Max Activating Token Index: 390