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

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

Neuron 1977 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: 1.2356. Min Range: -1.2356

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1447169 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 1.2356. Min Range: -1.2356

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1461433 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 1.2356. Min Range: -1.2356

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1366036 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 1.2356. Min Range: -1.2356

Max Act: 1.0231. Min Act: -0.0001

Data Index: 1229652 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1442377 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1389895 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1412769 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1525651 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9228. Min Act: -0.0001

Data Index: 3732 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1380700 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1430882 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1450053 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1425039 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1598799 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8847. Min Act: -0.0000

Data Index: 389247 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1600946 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8868. Min Act: -0.0000

Data Index: 873877 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1364026 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9153. Min Act: -0.0000

Data Index: 957817 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1452939 (Python Code)

Max Activating Token Index: 697