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

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

Neuron 4872 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: 2.2610. Min Range: -2.2610

Max Act: 2.2610. Min Act: -0.0001

Data Index: 1387645 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 2.2610. Min Range: -2.2610

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1390065 (Python Code)

Max Activating Token Index: 181

Text #2

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.9817. Min Act: -0.0000

Data Index: 1625217 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 2.2610. Min Range: -2.2610

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1507574 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 2.2610. Min Range: -2.2610

Max Act: 2.0328. Min Act: -0.0000

Data Index: 1646205 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1480101 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.9689. Min Act: -0.0001

Data Index: 1509892 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.9526. Min Act: -0.0000

Data Index: 1592003 (Python Code)

Max Activating Token Index: 928

Text #8

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.6266. Min Act: -0.0000

Data Index: 1570876 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1654819 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.8844. Min Act: -0.0000

Data Index: 1538836 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.7757. Min Act: -0.0000

Data Index: 1502629 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.8824. Min Act: -0.0000

Data Index: 1489282 (Python Code)

Max Activating Token Index: 546

Text #13

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.8259. Min Act: -0.0000

Data Index: 1616423 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.8982. Min Act: -0.0000

Data Index: 1418354 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1411531 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.8073. Min Act: -0.0000

Data Index: 1637767 (Python Code)

Max Activating Token Index: 685

Text #17

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1388154 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.7837. Min Act: -0.0000

Data Index: 1486639 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 2.2610. Min Range: -2.2610

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1416558 (Python Code)

Max Activating Token Index: 377