Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3441 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1557015 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.6714. Min Act: -0.0000

Data Index: 1447346 (Python Code)

Max Activating Token Index: 460

Text #2

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.6022. Min Act: -0.0000

Data Index: 1637018 (Python Code)

Max Activating Token Index: 516

Text #3

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.3452. Min Act: -0.0000

Data Index: 1427107 (Python Code)

Max Activating Token Index: 265

Text #4

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.5753. Min Act: -0.0000

Data Index: 1402599 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.3609. Min Act: -0.0000

Data Index: 1613480 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.3361. Min Act: -0.0000

Data Index: 1409869 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.2941. Min Act: -0.0000

Data Index: 1407951 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1681. Min Act: -0.0000

Data Index: 1403479 (Python Code)

Max Activating Token Index: 987

Text #9

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.5110. Min Act: -0.0000

Data Index: 11334 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1073. Min Act: -0.0000

Data Index: 1546181 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.3599. Min Act: -0.0000

Data Index: 1491534 (Python Code)

Max Activating Token Index: 619

Text #12

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1308. Min Act: -0.0000

Data Index: 1472656 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.0651. Min Act: -0.0000

Data Index: 1506143 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1593. Min Act: -0.0000

Data Index: 1402394 (Python Code)

Max Activating Token Index: 413

Text #15

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1617. Min Act: -0.0000

Data Index: 1501286 (Python Code)

Max Activating Token Index: 74

Text #16

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.0352. Min Act: -0.0000

Data Index: 1458688 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1202. Min Act: -0.0000

Data Index: 904427 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.1047. Min Act: -0.0000

Data Index: 261931 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.7049. Min Range: -2.7049

Max Act: 2.2172. Min Act: -0.0000

Data Index: 1553825 (Python Code)

Max Activating Token Index: 934