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

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

Neuron 782 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: 1.5784. Min Range: -1.5784

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1645300 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.5784. Min Act: -0.0000

Data Index: 1527859 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1455519 (Python Code)

Max Activating Token Index: 275

Text #3

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1493980 (Python Code)

Max Activating Token Index: 980

Text #4

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1439876 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1413316 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1468198 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1525688 (Python Code)

Max Activating Token Index: 371

Text #8

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1497690 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1551205 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1614640 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1416984 (Python Code)

Max Activating Token Index: 290

Text #12

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1454116 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1572460 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 1.5784. Min Range: -1.5784

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1383384 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1544676 (Python Code)

Max Activating Token Index: 668

Text #16

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1595862 (Python Code)

Max Activating Token Index: 223

Text #17

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1573299 (Python Code)

Max Activating Token Index: 339

Text #18

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1520537 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 1.5784. Min Range: -1.5784

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1398987 (Python Code)

Max Activating Token Index: 571