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

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

Neuron 2914 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1499976 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1515335 (Python Code)

Max Activating Token Index: 438

Text #2

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1405745 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1452047 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1446568 (Python Code)

Max Activating Token Index: 323

Text #5

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1360113 (Python Code)

Max Activating Token Index: 775

Text #6

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1450062 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1402848 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1642160 (Python Code)

Max Activating Token Index: 152

Text #9

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1394030 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1415454 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1640175 (Python Code)

Max Activating Token Index: 728

Text #12

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1576234 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1425952 (Python Code)

Max Activating Token Index: 883

Text #14

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1626604 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1503431 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1575533 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1513394 (Python Code)

Max Activating Token Index: 599

Text #18

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1588576 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 0.7891. Min Range: -0.7891

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1509348 (Python Code)

Max Activating Token Index: 1014