Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3009 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.6744. Min Act: -0.0001
Data Index: 656384 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.1464. Min Act: -0.0001
Data Index: 358056 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.2795. Min Act: -0.0001
Data Index: 1271764 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.4595. Min Act: -0.0001
Data Index: 1591415 (Python Code)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.3969. Min Act: -0.0001
Data Index: 150185 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.2323. Min Act: -0.0001
Data Index: 1378505 (Python Code)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.5530. Min Act: -0.0001
Data Index: 1382463 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.0738. Min Act: -0.0001
Data Index: 676704 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.1664. Min Act: -0.0001
Data Index: 220195 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.3810. Min Act: -0.0001
Data Index: 1286859 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.1577. Min Act: -0.0001
Data Index: 181482 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.3582. Min Act: -0.0001
Data Index: 851828 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.2410. Min Act: -0.0001
Data Index: 1236892 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6744. Min Range: -2.6744
Max Act: 1.9891. Min Act: -0.0001
Data Index: 1372611 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.1145. Min Act: -0.0001
Data Index: 1501052 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.2063. Min Act: -0.0001
Data Index: 463455 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6744. Min Range: -2.6744
Max Act: 1.9862. Min Act: -0.0001
Data Index: 1191480 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6744. Min Range: -2.6744
Max Act: 1.9492. Min Act: -0.0001
Data Index: 503 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6744. Min Range: -2.6744
Max Act: 2.2050. Min Act: -0.0001
Data Index: 464474 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6744. Min Range: -2.6744
Max Act: 1.9329. Min Act: -0.0001
Data Index: 1180716 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19