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

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

Neuron 1553 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: 1.3760. Min Range: -1.3760

Max Act: 1.3760. Min Act: -0.0000

Data Index: 1532749 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1452162 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1397895 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1596536 (Python Code)

Max Activating Token Index: 362

Text #4

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0108. Min Act: -0.0000

Data Index: 1571596 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1597918 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1463662 (Python Code)

Max Activating Token Index: 160

Text #7

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1469404 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1554164 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1511650 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 1.3760. Min Range: -1.3760

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1364834 (Python Code)

Max Activating Token Index: 687

Text #11

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1459164 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1409083 (Python Code)

Max Activating Token Index: 354

Text #13

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1470908 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1573935 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1392512 (Python Code)

Max Activating Token Index: 341

Text #16

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1560526 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1579244 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1396248 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 1.3760. Min Range: -1.3760

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1531255 (Python Code)

Max Activating Token Index: 496