Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5480 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.8032. Min Act: -0.1700
Data Index: 5199208 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.8032. Min Act: -0.1700
Data Index: 5341941 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.8345. Min Act: -0.1700
Data Index: 6093917 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.8032. Min Act: -0.1700
Data Index: 4438324 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7720. Min Act: -0.1700
Data Index: 6530755 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7407. Min Act: -0.1700
Data Index: 3531115 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7407. Min Act: -0.1700
Data Index: 1790522 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7407. Min Act: -0.1700
Data Index: 2323696 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7407. Min Act: -0.1700
Data Index: 1735376 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7407. Min Act: -0.1700
Data Index: 7280597 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7407. Min Act: -0.1700
Data Index: 826111 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 6979557 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 1895627 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 7924412 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 3461225 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 4875441 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 5188721 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.7095. Min Act: -0.1700
Data Index: 3053554 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.6782. Min Act: -0.1700
Data Index: 4677828 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8345. Min Range: -5.8345
Max Act: 5.6782. Min Act: -0.1700
Data Index: 1778232 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19