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

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

Neuron 2549 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: 2.7657. Min Range: -2.7657

Max Act: 2.7657. Min Act: -0.0000

Data Index: 1486207 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.4339. Min Act: -0.0000

Data Index: 1610921 (Python Code)

Max Activating Token Index: 620

Text #2

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.4162. Min Act: -0.0000

Data Index: 1606557 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.6497. Min Act: -0.0000

Data Index: 1570577 (Python Code)

Max Activating Token Index: 160

Text #4

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.6241. Min Act: -0.0000

Data Index: 1553179 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.4381. Min Act: -0.0000

Data Index: 1649290 (Python Code)

Max Activating Token Index: 629

Text #6

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.1520. Min Act: -0.0000

Data Index: 1577374 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.3018. Min Act: -0.0000

Data Index: 1464051 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.1627. Min Act: -0.0000

Data Index: 1449691 (Python Code)

Max Activating Token Index: 569

Text #9

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.2825. Min Act: -0.0000

Data Index: 1590692 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.0202. Min Act: -0.0000

Data Index: 1429895 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.2379. Min Act: -0.0000

Data Index: 1487735 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1455802 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1648376 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.2322. Min Act: -0.0000

Data Index: 1409971 (Python Code)

Max Activating Token Index: 322

Text #15

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.0776. Min Act: -0.0000

Data Index: 1474365 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.0764. Min Act: -0.0000

Data Index: 1498153 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 2.7657. Min Range: -2.7657

Max Act: 1.9327. Min Act: -0.0000

Data Index: 448691 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 2.7657. Min Range: -2.7657

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1553510 (Python Code)

Max Activating Token Index: 834

Text #19

Max Range: 2.7657. Min Range: -2.7657

Max Act: 2.0723. Min Act: -0.0000

Data Index: 1553683 (Python Code)

Max Activating Token Index: 257