Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3836 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.4416. Min Act: -0.0001
Data Index: 1377524 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3850. Min Act: -0.0001
Data Index: 1578433 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3596. Min Act: -0.0001
Data Index: 1604831 (Python Code)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3955. Min Act: -0.0001
Data Index: 1410854 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3400. Min Act: -0.0001
Data Index: 1436256 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3457. Min Act: -0.0001
Data Index: 1546099 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3724. Min Act: -0.0001
Data Index: 1457351 (Python Code)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3119. Min Act: -0.0001
Data Index: 1513067 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3770. Min Act: -0.0001
Data Index: 1643592 (Python Code)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3488. Min Act: -0.0001
Data Index: 1532837 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3571. Min Act: -0.0001
Data Index: 1387882 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3418. Min Act: -0.0001
Data Index: 1455857 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.2851. Min Act: -0.0001
Data Index: 1655322 (Python Code)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3159. Min Act: -0.0001
Data Index: 1610303 (Python Code)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3357. Min Act: -0.0001
Data Index: 1365831 (Python Code)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3267. Min Act: -0.0001
Data Index: 1481633 (Python Code)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3344. Min Act: -0.0001
Data Index: 1556532 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3330. Min Act: -0.0001
Data Index: 1451792 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3329. Min Act: -0.0001
Data Index: 1451773 (Python Code)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4416. Min Range: -0.4416
Max Act: 0.3427. Min Act: -0.0001
Data Index: 1450590 (Python Code)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19