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

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

Neuron 2397 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.7800. Min Act: -0.0002

Data Index: 27986 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.2522. Min Act: -0.0002

Data Index: 1376548 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.2552. Min Act: -0.0002

Data Index: 1457491 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.2084. Min Act: -0.0002

Data Index: 582527 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1952. Min Act: -0.0002

Data Index: 577008 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1807. Min Act: -0.0002

Data Index: 409082 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1150. Min Act: -0.0002

Data Index: 700174 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1566. Min Act: -0.0002

Data Index: 1354372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1018. Min Act: -0.0002

Data Index: 1407461 (Python Code)

Max Activating Token Index: 388

Text #9

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1248. Min Act: -0.0002

Data Index: 1195767 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1056. Min Act: -0.0002

Data Index: 1628953 (Python Code)

Max Activating Token Index: 429

Text #11

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1225. Min Act: -0.0002

Data Index: 6977 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.1115. Min Act: -0.0002

Data Index: 1387368 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0764. Min Act: -0.0002

Data Index: 1560672 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0825. Min Act: -0.0002

Data Index: 1639092 (Python Code)

Max Activating Token Index: 103

Text #15

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0195. Min Act: -0.0003

Data Index: 931531 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0421. Min Act: -0.0002

Data Index: 1592822 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0427. Min Act: -0.0002

Data Index: 1288151 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0171. Min Act: -0.0002

Data Index: 1464200 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 1.7800. Min Range: -1.7800

Max Act: 1.0284. Min Act: -0.0002

Data Index: 1426475 (Python Code)

Max Activating Token Index: 777