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

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

Neuron 3950 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: 5.2798. Min Range: -5.2798

Max Act: 4.5798. Min Act: -0.0001

Data Index: 1609065 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 5.2798. Min Range: -5.2798

Max Act: 5.2798. Min Act: -0.0001

Data Index: 1583683 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9072. Min Act: -0.0001

Data Index: 1517514 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6754. Min Act: -0.0001

Data Index: 1485403 (Python Code)

Max Activating Token Index: 582

Text #4

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9024. Min Act: -0.0001

Data Index: 1466706 (Python Code)

Max Activating Token Index: 932

Text #5

Max Range: 5.2798. Min Range: -5.2798

Max Act: 5.0840. Min Act: -0.0001

Data Index: 1511345 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9018. Min Act: -0.0001

Data Index: 1469352 (Python Code)

Max Activating Token Index: 741

Text #7

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8917. Min Act: -0.0001

Data Index: 1498123 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9076. Min Act: -0.0001

Data Index: 1581509 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 5.2798. Min Range: -5.2798

Max Act: 5.0492. Min Act: -0.0001

Data Index: 1401075 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6779. Min Act: -0.0001

Data Index: 1472229 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 5.2798. Min Range: -5.2798

Max Act: 5.1540. Min Act: -0.0001

Data Index: 1510544 (Python Code)

Max Activating Token Index: 592

Text #12

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9496. Min Act: -0.0001

Data Index: 1422139 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5805. Min Act: -0.0001

Data Index: 1444391 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9194. Min Act: -0.0001

Data Index: 1474000 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5700. Min Act: -0.0001

Data Index: 1388155 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.2408. Min Act: -0.0001

Data Index: 1468692 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8976. Min Act: -0.0001

Data Index: 1504723 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 5.2798. Min Range: -5.2798

Max Act: 5.0463. Min Act: -0.0001

Data Index: 1467969 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8475. Min Act: -0.0001

Data Index: 1505695 (Python Code)

Max Activating Token Index: 954