Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 901 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.6069. Min Act: -0.1700
Data Index: 1523928 (Python Code)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.6069. Min Act: -0.1700
Data Index: 1361346 (Python Code)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.6069. Min Act: -0.1700
Data Index: 1510991 (Python Code)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.5444. Min Act: -0.1700
Data Index: 1562660 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.5444. Min Act: -0.1700
Data Index: 1476786 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.5444. Min Act: -0.1700
Data Index: 1504364 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.5444. Min Act: -0.1700
Data Index: 1505894 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.5444. Min Act: -0.1700
Data Index: 1391873 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.5132. Min Act: -0.1700
Data Index: 1512569 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4507. Min Act: -0.1700
Data Index: 1621775 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4507. Min Act: -0.1700
Data Index: 249478 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4507. Min Act: -0.1700
Data Index: 1602742 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4194. Min Act: -0.1700
Data Index: 1650912 (Python Code)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4507. Min Act: -0.1700
Data Index: 1595124 (Python Code)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4507. Min Act: -0.1700
Data Index: 1441113 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4819. Min Act: -0.1700
Data Index: 1471126 (Python Code)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4819. Min Act: -0.1700
Data Index: 1531120 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4819. Min Act: -0.1700
Data Index: 1482831 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4194. Min Act: -0.1700
Data Index: 1377591 (Python Code)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6069. Min Range: -4.6069
Max Act: 4.4507. Min Act: -0.1700
Data Index: 898612 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19