Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.5900. Min Range: -5.5900

Max Act: 5.5900. Min Act: -0.0001

Data Index: 1544040 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 5.5900. Min Range: -5.5900

Max Act: 5.3610. Min Act: -0.0001

Data Index: 1536933 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.8883. Min Act: -0.0000

Data Index: 1367614 (Python Code)

Max Activating Token Index: 483

Text #3

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.6768. Min Act: -0.0001

Data Index: 1446280 (Python Code)

Max Activating Token Index: 855

Text #4

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.3763. Min Act: -0.0000

Data Index: 1521620 (Python Code)

Max Activating Token Index: 906

Text #5

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.3600. Min Act: -0.0000

Data Index: 1607590 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.3710. Min Act: -0.0000

Data Index: 1409231 (Python Code)

Max Activating Token Index: 923

Text #7

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.5184. Min Act: -0.0001

Data Index: 1483237 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.2969. Min Act: -0.0000

Data Index: 1590302 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.2189. Min Act: -0.0001

Data Index: 1539719 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.2108. Min Act: -0.0001

Data Index: 1478389 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.4359. Min Act: -0.0001

Data Index: 1646952 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.1512. Min Act: -0.0001

Data Index: 1506075 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.3058. Min Act: -0.0000

Data Index: 1559572 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.2669. Min Act: -0.0000

Data Index: 1427991 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.2146. Min Act: -0.0001

Data Index: 1545105 (Python Code)

Max Activating Token Index: 731

Text #16

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.4228. Min Act: -0.0000

Data Index: 1074937 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.1089. Min Act: -0.0001

Data Index: 1517735 (Python Code)

Max Activating Token Index: 905

Text #18

Max Range: 5.5900. Min Range: -5.5900

Max Act: 4.2392. Min Act: -0.0000

Data Index: 1408169 (Python Code)

Max Activating Token Index: 973

Text #19

Max Range: 5.5900. Min Range: -5.5900

Max Act: 3.7245. Min Act: -0.0001

Data Index: 1499532 (Python Code)

Max Activating Token Index: 720