Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3763 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0141. Min Range: -2.0141

Max Act: 2.0141. Min Act: -0.0000

Data Index: 918524 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.7861. Min Act: -0.0000

Data Index: 1455437 (Python Code)

Max Activating Token Index: 256

Text #2

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.7839. Min Act: -0.0000

Data Index: 1624826 (Python Code)

Max Activating Token Index: 497

Text #3

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1656886 (Python Code)

Max Activating Token Index: 700

Text #4

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.7764. Min Act: -0.0000

Data Index: 1482919 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.4914. Min Act: -0.0000

Data Index: 1578167 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1546558 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1479762 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.2373. Min Act: -0.0000

Data Index: 1652575 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1620031 (Python Code)

Max Activating Token Index: 880

Text #10

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1554988 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.2895. Min Act: -0.0000

Data Index: 1530431 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1625787 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1636191 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1386616 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.1907. Min Act: -0.0000

Data Index: 1376001 (Python Code)

Max Activating Token Index: 757

Text #16

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1414938 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1542775 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.1871. Min Act: -0.0000

Data Index: 1538768 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 2.0141. Min Range: -2.0141

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1409304 (Python Code)

Max Activating Token Index: 138