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

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

Neuron 4896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2919. Min Act: -0.0001

Data Index: 134379 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2159. Min Act: -0.0001

Data Index: 919525 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2178. Min Act: -0.0001

Data Index: 754746 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2065. Min Act: -0.0001

Data Index: 1615284 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2203. Min Act: -0.0001

Data Index: 1066575 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2200. Min Act: -0.0001

Data Index: 977004 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1303153 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2089. Min Act: -0.0001

Data Index: 818006 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1100571 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1072730 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2022. Min Act: -0.0001

Data Index: 596672 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2006. Min Act: -0.0001

Data Index: 667029 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1315597 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1967. Min Act: -0.0001

Data Index: 212710 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1896. Min Act: -0.0001

Data Index: 113112 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1347052 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1569539 (Python Code)

Max Activating Token Index: 448

Text #17

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1645263 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1011820 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.2919. Min Range: -0.2919

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1440977 (Python Code)

Max Activating Token Index: 211