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

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

Neuron 2022 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1374598 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1465975 (Python Code)

Max Activating Token Index: 228

Text #2

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1529838 (Python Code)

Max Activating Token Index: 399

Text #3

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1507043 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1367951 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1471486 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1596962 (Python Code)

Max Activating Token Index: 196

Text #7

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1362642 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1535653 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1569294 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1511060 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1498422 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1490336 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1534050 (Python Code)

Max Activating Token Index: 229

Text #14

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1656756 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1427490 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5903. Min Act: -0.0000

Data Index: 1524781 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1516168 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1484496 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.8443. Min Range: -0.8443

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1455366 (Python Code)

Max Activating Token Index: 745