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

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

Neuron 3096 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.3622. Min Act: -0.0000

Data Index: 1653497 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.3191. Min Act: -0.0000

Data Index: 1409434 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.3570. Min Act: -0.0000

Data Index: 1463937 (Python Code)

Max Activating Token Index: 355

Text #3

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.2489. Min Act: -0.0000

Data Index: 1426099 (Python Code)

Max Activating Token Index: 425

Text #4

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.1655. Min Act: -0.0000

Data Index: 1535887 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.1150. Min Act: -0.0000

Data Index: 1482680 (Python Code)

Max Activating Token Index: 156

Text #6

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1431190 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.0913. Min Act: -0.0000

Data Index: 1464437 (Python Code)

Max Activating Token Index: 206

Text #8

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.0665. Min Act: -0.0000

Data Index: 1632809 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.0593. Min Act: -0.0000

Data Index: 1633947 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 2.3622. Min Range: -2.3622

Max Act: 2.0426. Min Act: -0.0000

Data Index: 1528966 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.9357. Min Act: -0.0000

Data Index: 1409977 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.8901. Min Act: -0.0000

Data Index: 1475905 (Python Code)

Max Activating Token Index: 358

Text #13

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.7300. Min Act: -0.0000

Data Index: 1440100 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.9014. Min Act: -0.0000

Data Index: 1582313 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1475739 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.8663. Min Act: -0.0000

Data Index: 1402409 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.7849. Min Act: -0.0000

Data Index: 1443527 (Python Code)

Max Activating Token Index: 221

Text #18

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.8132. Min Act: -0.0000

Data Index: 1367226 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 2.3622. Min Range: -2.3622

Max Act: 1.8358. Min Act: -0.0000

Data Index: 1586027 (Python Code)

Max Activating Token Index: 428