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

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

Neuron 1239 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: 1.2534. Min Range: -1.2534

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1559269 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.1963. Min Act: -0.0000

Data Index: 740921 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1507696 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1514079 (Python Code)

Max Activating Token Index: 497

Text #4

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1574347 (Python Code)

Max Activating Token Index: 293

Text #5

Max Range: 1.2534. Min Range: -1.2534

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1588006 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9463. Min Act: -0.0000

Data Index: 1567565 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1535156 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9255. Min Act: -0.0000

Data Index: 200851 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1590364 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8329. Min Act: -0.0000

Data Index: 129821 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1504046 (Python Code)

Max Activating Token Index: 74

Text #12

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1651484 (Python Code)

Max Activating Token Index: 982

Text #13

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1016461 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1451485 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1519335 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8583. Min Act: -0.0000

Data Index: 610424 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1580810 (Python Code)

Max Activating Token Index: 524

Text #18

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1294204 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.2534. Min Range: -1.2534

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1331315 (C4 (Web Text))

Max Activating Token Index: 227