Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1790 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.5635. Min Act: -0.1700
Data Index: 1085347 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.5010. Min Act: -0.1700
Data Index: 1063877 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.3447. Min Act: -0.1700
Data Index: 855364 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.3134. Min Act: -0.1700
Data Index: 776324 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.3760. Min Act: -0.1700
Data Index: 1138375 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2978. Min Act: -0.1700
Data Index: 684118 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2978. Min Act: -0.1700
Data Index: 134624 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2978. Min Act: -0.1697
Data Index: 516615 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2666. Min Act: -0.1700
Data Index: 434990 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2978. Min Act: -0.1700
Data Index: 673244 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2666. Min Act: -0.1700
Data Index: 454264 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2666. Min Act: -0.1700
Data Index: 875029 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2353. Min Act: -0.1700
Data Index: 185406 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2353. Min Act: -0.1700
Data Index: 581480 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2353. Min Act: -0.1700
Data Index: 34883 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2353. Min Act: -0.1700
Data Index: 124527 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2041. Min Act: -0.1700
Data Index: 23049 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2041. Min Act: -0.1700
Data Index: 503005 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2041. Min Act: -0.1700
Data Index: 848263 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5635. Min Range: -4.5635
Max Act: 4.2041. Min Act: -0.1700
Data Index: 328240 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19