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

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

Neuron 1480 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8898. Min Act: -0.0001

Data Index: 1597145 (Python Code)

Max Activating Token Index: 202

Text #1

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.8770. Min Act: -0.0001

Data Index: 1583990 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1499382 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1456431 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1408265 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6517. Min Act: -0.0001

Data Index: 1525043 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1510085 (Python Code)

Max Activating Token Index: 369

Text #7

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1493915 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1427924 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1557176 (Python Code)

Max Activating Token Index: 493

Text #10

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6135. Min Act: -0.0001

Data Index: 1431727 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1463739 (Python Code)

Max Activating Token Index: 162

Text #12

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6228. Min Act: -0.0001

Data Index: 1633659 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1415609 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1521919 (Python Code)

Max Activating Token Index: 831

Text #15

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1541855 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1638623 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1595741 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1571391 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 0.8898. Min Range: -0.8898

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1533281 (Python Code)

Max Activating Token Index: 919