Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 294 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0063. Min Range: -3.0063
Max Act: 3.0063. Min Act: -0.1700
Data Index: 1345166 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0063. Min Range: -3.0063
Max Act: 3.0063. Min Act: -0.1700
Data Index: 465375 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9905. Min Act: -0.1700
Data Index: 1135739 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9746. Min Act: -0.1700
Data Index: 781085 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9746. Min Act: -0.1700
Data Index: 627617 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1343315 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1071721 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9588. Min Act: -0.1700
Data Index: 1310138 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9588. Min Act: -0.1700
Data Index: 440772 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1346450 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1186208 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9430. Min Act: -0.1700
Data Index: 797454 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9430. Min Act: -0.1700
Data Index: 645879 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9271. Min Act: -0.1700
Data Index: 276967 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9113. Min Act: -0.1700
Data Index: 675075 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9271. Min Act: -0.1700
Data Index: 1214964 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9113. Min Act: -0.1700
Data Index: 1287096 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9271. Min Act: -0.1700
Data Index: 359625 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9271. Min Act: -0.1700
Data Index: 363201 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0063. Min Range: -3.0063
Max Act: 2.9113. Min Act: -0.1700
Data Index: 225463 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19