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

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

Neuron 2956 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4988. Min Range: -6.4988

Max Act: 6.0520. Min Act: -0.0000

Data Index: 1566335 (Python Code)

Max Activating Token Index: 638

Text #1

Max Range: 6.4988. Min Range: -6.4988

Max Act: 6.4988. Min Act: -0.0000

Data Index: 1424663 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.2628. Min Act: -0.0000

Data Index: 1573181 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.5465. Min Act: -0.0000

Data Index: 1528041 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.6763. Min Act: -0.0000

Data Index: 1395673 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.4914. Min Act: -0.0000

Data Index: 1433719 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.3073. Min Act: -0.0000

Data Index: 1568173 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.2330. Min Act: -0.0000

Data Index: 1362463 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.2121. Min Act: -0.0000

Data Index: 1546241 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.0253. Min Act: -0.0000

Data Index: 1491904 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.3211. Min Act: -0.0001

Data Index: 1365279 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.0108. Min Act: -0.0000

Data Index: 1373015 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.1242. Min Act: -0.0000

Data Index: 1526936 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.1272. Min Act: -0.0000

Data Index: 1533863 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.3018. Min Act: -0.0000

Data Index: 1580901 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.9063. Min Act: -0.0000

Data Index: 1649741 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 6.4988. Min Range: -6.4988

Max Act: 5.0824. Min Act: -0.0001

Data Index: 1647272 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.9672. Min Act: -0.0000

Data Index: 1488511 (Python Code)

Max Activating Token Index: 221

Text #18

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.9411. Min Act: -0.0001

Data Index: 1599247 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 6.4988. Min Range: -6.4988

Max Act: 4.7638. Min Act: -0.0000

Data Index: 1410116 (Python Code)

Max Activating Token Index: 206