Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5511 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3711. Min Range: -6.3711
Max Act: 6.3711. Min Act: -0.1700
Data Index: 481041 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3711. Min Range: -6.3711
Max Act: 6.2773. Min Act: -0.1700
Data Index: 4510261 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.8711. Min Act: -0.1700
Data Index: 862934 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.8711. Min Act: -0.1700
Data Index: 5019146 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.7773. Min Act: -0.1700
Data Index: 1611027 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.7148. Min Act: -0.1700
Data Index: 4322663 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.7148. Min Act: -0.1700
Data Index: 2188513 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.6523. Min Act: -0.1700
Data Index: 2952818 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.6211. Min Act: -0.1700
Data Index: 7078805 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5586. Min Act: -0.1700
Data Index: 2049869 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.6211. Min Act: -0.1700
Data Index: 7300095 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5586. Min Act: -0.1700
Data Index: 1831722 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5898. Min Act: -0.1700
Data Index: 5941573 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5898. Min Act: -0.1700
Data Index: 5851458 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5586. Min Act: -0.1700
Data Index: 2065351 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5586. Min Act: -0.1700
Data Index: 4599046 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5586. Min Act: -0.1700
Data Index: 206079 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5586. Min Act: -0.1700
Data Index: 5031460 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5273. Min Act: -0.1700
Data Index: 4207592 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3711. Min Range: -6.3711
Max Act: 5.5273. Min Act: -0.1700
Data Index: 5633250 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19