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

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

Neuron 4691 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: 3.2325. Min Range: -3.2325

Max Act: 2.9721. Min Act: -0.0000

Data Index: 1601816 (Python Code)

Max Activating Token Index: 223

Text #1

Max Range: 3.2325. Min Range: -3.2325

Max Act: 3.0991. Min Act: -0.0000

Data Index: 1388717 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 3.2325. Min Range: -3.2325

Max Act: 3.2325. Min Act: -0.0000

Data Index: 1402842 (Python Code)

Max Activating Token Index: 288

Text #3

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.8528. Min Act: -0.0000

Data Index: 1409472 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.5790. Min Act: -0.0000

Data Index: 1412282 (Python Code)

Max Activating Token Index: 953

Text #5

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.3891. Min Act: -0.0000

Data Index: 1379321 (Python Code)

Max Activating Token Index: 193

Text #6

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.7443. Min Act: -0.0000

Data Index: 1568038 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.3849. Min Act: -0.0000

Data Index: 1634865 (Python Code)

Max Activating Token Index: 172

Text #8

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.3775. Min Act: -0.0000

Data Index: 1360277 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1620522 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.3508. Min Act: -0.0000

Data Index: 1600773 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.2877. Min Act: -0.0000

Data Index: 1601531 (Python Code)

Max Activating Token Index: 813

Text #12

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.0115. Min Act: -0.0000

Data Index: 1468797 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.0077. Min Act: -0.0000

Data Index: 1654950 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.2114. Min Act: -0.0000

Data Index: 1519282 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 3.2325. Min Range: -3.2325

Max Act: 1.9409. Min Act: -0.0000

Data Index: 1435977 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.2325. Min Range: -3.2325

Max Act: 1.9446. Min Act: -0.0000

Data Index: 1360093 (Python Code)

Max Activating Token Index: 687

Text #17

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.0082. Min Act: -0.0000

Data Index: 1583249 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.0344. Min Act: -0.0000

Data Index: 1641488 (Python Code)

Max Activating Token Index: 819

Text #19

Max Range: 3.2325. Min Range: -3.2325

Max Act: 2.0312. Min Act: -0.0000

Data Index: 1587795 (Python Code)

Max Activating Token Index: 89