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

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

Neuron 4834 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1539202 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1551563 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1432529 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1597710 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1408831 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1595766 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1496119 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1425799 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1432354 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1465781 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1414214 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1466269 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1462818 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1509019 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1366660 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1405509 (Python Code)

Max Activating Token Index: 741

Text #16

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1647943 (Python Code)

Max Activating Token Index: 845

Text #17

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1570644 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1587746 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.7182. Min Range: -0.7182

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1419092 (Python Code)

Max Activating Token Index: 1022