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

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

Neuron 94 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.3941. Min Act: -0.0000

Data Index: 1645745 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 3.3941. Min Range: -3.3941

Max Act: 3.1289. Min Act: -0.0000

Data Index: 1529306 (Python Code)

Max Activating Token Index: 758

Text #2

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.9177. Min Act: -0.0000

Data Index: 1532903 (Python Code)

Max Activating Token Index: 354

Text #3

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.5880. Min Act: -0.0000

Data Index: 1466586 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.4828. Min Act: -0.0000

Data Index: 1464103 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.1464. Min Act: -0.0000

Data Index: 1592837 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.2116. Min Act: -0.0000

Data Index: 1465224 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.2517. Min Act: -0.0000

Data Index: 1453725 (Python Code)

Max Activating Token Index: 88

Text #8

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.2300. Min Act: -0.0000

Data Index: 1389949 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.1744. Min Act: -0.0000

Data Index: 1513477 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.9791. Min Act: -0.0000

Data Index: 1653904 (Python Code)

Max Activating Token Index: 401

Text #11

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.0680. Min Act: -0.0000

Data Index: 1654247 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.9176. Min Act: -0.0000

Data Index: 1480787 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.9103. Min Act: -0.0000

Data Index: 1584430 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.8248. Min Act: -0.0000

Data Index: 1535702 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.8130. Min Act: -0.0000

Data Index: 1571983 (Python Code)

Max Activating Token Index: 811

Text #16

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.8173. Min Act: -0.0000

Data Index: 1549510 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.8025. Min Act: -0.0000

Data Index: 1407515 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 3.3941. Min Range: -3.3941

Max Act: 2.0089. Min Act: -0.0000

Data Index: 1506392 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 3.3941. Min Range: -3.3941

Max Act: 1.7932. Min Act: -0.0000

Data Index: 1589060 (Python Code)

Max Activating Token Index: 572