Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1644 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3166. Min Range: -4.3166
Max Act: 4.3166. Min Act: -0.1700
Data Index: 505058 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3166. Min Range: -4.3166
Max Act: 4.1603. Min Act: -0.1700
Data Index: 922442 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3166. Min Range: -4.3166
Max Act: 4.0665. Min Act: -0.1700
Data Index: 1046434 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3166. Min Range: -4.3166
Max Act: 4.0353. Min Act: -0.1700
Data Index: 1173252 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9727. Min Act: -0.1700
Data Index: 1249520 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9415. Min Act: -0.1700
Data Index: 756107 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9102. Min Act: -0.1700
Data Index: 835993 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.8789. Min Act: -0.1700
Data Index: 949240 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9727. Min Act: -0.1700
Data Index: 285289 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.8789. Min Act: -0.1700
Data Index: 854407 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.8789. Min Act: -0.1700
Data Index: 1026623 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9415. Min Act: -0.1700
Data Index: 90182 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9102. Min Act: -0.1700
Data Index: 579424 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.8789. Min Act: -0.1700
Data Index: 1339030 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9102. Min Act: -0.1700
Data Index: 146635 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9102. Min Act: -0.1700
Data Index: 1349075 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.9415. Min Act: -0.1700
Data Index: 1177656 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.8789. Min Act: -0.1700
Data Index: 1204368 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.7851. Min Act: -0.1700
Data Index: 271439 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3166. Min Range: -4.3166
Max Act: 3.8789. Min Act: -0.1700
Data Index: 633320 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19