Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2187 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1889. Min Act: -0.0000

Data Index: 562978 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1334. Min Act: -0.0001

Data Index: 1520678 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1217. Min Act: -0.0001

Data Index: 1375030 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1096973 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1374. Min Act: -0.0001

Data Index: 1645165 (Python Code)

Max Activating Token Index: 964

Text #5

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0890. Min Act: -0.0001

Data Index: 1624769 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0707. Min Act: -0.0001

Data Index: 1447502 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0598. Min Act: -0.0001

Data Index: 1632559 (Python Code)

Max Activating Token Index: 283

Text #8

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1238. Min Act: -0.0001

Data Index: 1607048 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0261. Min Act: -0.0001

Data Index: 1383640 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0959. Min Act: -0.0001

Data Index: 726136 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0483. Min Act: -0.0001

Data Index: 1647390 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.1013. Min Act: -0.0001

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0005. Min Act: -0.0001

Data Index: 1402220 (Python Code)

Max Activating Token Index: 571

Text #14

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0227. Min Act: -0.0001

Data Index: 1395160 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1294551 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.9782. Min Act: -0.0001

Data Index: 1378352 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1603290 (Python Code)

Max Activating Token Index: 983

Text #18

Max Range: 1.1889. Min Range: -1.1889

Max Act: 1.0270. Min Act: -0.0001

Data Index: 1385741 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 1.1889. Min Range: -1.1889

Max Act: 0.9898. Min Act: -0.0001

Data Index: 1634001 (Python Code)

Max Activating Token Index: 470