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

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

Neuron 5335 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2307. Min Range: -5.2307

Max Act: 5.2307. Min Act: -0.0000

Data Index: 1479044 (Python Code)

Max Activating Token Index: 927

Text #1

Max Range: 5.2307. Min Range: -5.2307

Max Act: 4.7062. Min Act: -0.0000

Data Index: 1541726 (Python Code)

Max Activating Token Index: 976

Text #2

Max Range: 5.2307. Min Range: -5.2307

Max Act: 4.4325. Min Act: -0.0000

Data Index: 1472299 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 5.2307. Min Range: -5.2307

Max Act: 4.7401. Min Act: -0.0000

Data Index: 1546112 (Python Code)

Max Activating Token Index: 672

Text #4

Max Range: 5.2307. Min Range: -5.2307

Max Act: 3.3632. Min Act: -0.0000

Data Index: 1451428 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 5.2307. Min Range: -5.2307

Max Act: 3.3495. Min Act: -0.0000

Data Index: 1420261 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.8121. Min Act: -0.0000

Data Index: 1401202 (Python Code)

Max Activating Token Index: 949

Text #7

Max Range: 5.2307. Min Range: -5.2307

Max Act: 3.5244. Min Act: -0.0000

Data Index: 1436947 (Python Code)

Max Activating Token Index: 816

Text #8

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.9747. Min Act: -0.0000

Data Index: 221048 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 5.2307. Min Range: -5.2307

Max Act: 3.1047. Min Act: -0.0000

Data Index: 1522287 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 5.2307. Min Range: -5.2307

Max Act: 3.3658. Min Act: -0.0000

Data Index: 1433842 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 5.2307. Min Range: -5.2307

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1635226 (Python Code)

Max Activating Token Index: 149

Text #12

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.8291. Min Act: -0.0000

Data Index: 1575946 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.7738. Min Act: -0.0000

Data Index: 1581964 (Python Code)

Max Activating Token Index: 529

Text #14

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.7803. Min Act: -0.0000

Data Index: 1526866 (Python Code)

Max Activating Token Index: 470

Text #15

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1435677 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.9102. Min Act: -0.0000

Data Index: 1634349 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1466301 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.6225. Min Act: -0.0000

Data Index: 886234 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 5.2307. Min Range: -5.2307

Max Act: 2.8831. Min Act: -0.0000

Data Index: 1477994 (Python Code)

Max Activating Token Index: 717