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

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

Neuron 368 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: 0.8839. Min Range: -0.8839

Max Act: 0.8839. Min Act: -0.0001

Data Index: 1525400 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8706. Min Act: -0.0001

Data Index: 1647878 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1400599 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7582. Min Act: -0.0001

Data Index: 1603646 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7196. Min Act: -0.0001

Data Index: 1411713 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1553823 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7527. Min Act: -0.0001

Data Index: 1639267 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1412799 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1558207 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1411466 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.5989. Min Act: -0.0001

Data Index: 1466920 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6181. Min Act: -0.0001

Data Index: 1635502 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6527. Min Act: -0.0001

Data Index: 1626961 (Python Code)

Max Activating Token Index: 398

Text #13

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1618170 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1398986 (Python Code)

Max Activating Token Index: 446

Text #15

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.6022. Min Act: -0.0000

Data Index: 565833 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1423806 (Python Code)

Max Activating Token Index: 299

Text #17

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.5923. Min Act: -0.0001

Data Index: 1443954 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1574942 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 0.8839. Min Range: -0.8839

Max Act: 0.5755. Min Act: -0.0001

Data Index: 1476542 (Python Code)

Max Activating Token Index: 263