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

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

Neuron 76 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3215. Min Range: -7.3215

Max Act: 7.3215. Min Act: -0.0000

Data Index: 1443928 (Python Code)

Max Activating Token Index: 584

Text #1

Max Range: 7.3215. Min Range: -7.3215

Max Act: 5.1198. Min Act: -0.0000

Data Index: 1417344 (Python Code)

Max Activating Token Index: 628

Text #2

Max Range: 7.3215. Min Range: -7.3215

Max Act: 4.5101. Min Act: -0.0000

Data Index: 1405379 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 7.3215. Min Range: -7.3215

Max Act: 4.4587. Min Act: -0.0000

Data Index: 1515830 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 7.3215. Min Range: -7.3215

Max Act: 4.0024. Min Act: -0.0000

Data Index: 1488010 (Python Code)

Max Activating Token Index: 791

Text #5

Max Range: 7.3215. Min Range: -7.3215

Max Act: 4.3642. Min Act: -0.0000

Data Index: 1512679 (Python Code)

Max Activating Token Index: 530

Text #6

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.9314. Min Act: -0.0000

Data Index: 1433551 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.9237. Min Act: -0.0000

Data Index: 1508171 (Python Code)

Max Activating Token Index: 844

Text #8

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.7471. Min Act: -0.0000

Data Index: 1528624 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.2856. Min Act: -0.0000

Data Index: 1549354 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.3837. Min Act: -0.0000

Data Index: 1632323 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.4823. Min Act: -0.0000

Data Index: 1527778 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.2525. Min Act: -0.0000

Data Index: 1413082 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.3084. Min Act: -0.0000

Data Index: 1582911 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.3638. Min Act: -0.0000

Data Index: 1533744 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.1182. Min Act: -0.0000

Data Index: 1616486 (Python Code)

Max Activating Token Index: 840

Text #16

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.4542. Min Act: -0.0000

Data Index: 1522148 (Python Code)

Max Activating Token Index: 903

Text #17

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.1039. Min Act: -0.0000

Data Index: 1478760 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.2578. Min Act: -0.0000

Data Index: 1545497 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 7.3215. Min Range: -7.3215

Max Act: 3.2004. Min Act: -0.0000

Data Index: 1369297 (Python Code)

Max Activating Token Index: 833