Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 791 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.8598. Min Act: -0.1700
Data Index: 5112586 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.8598. Min Act: -0.1700
Data Index: 196845 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.8121. Min Act: -0.1700
Data Index: 6036109 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7961. Min Act: -0.1700
Data Index: 5619006 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7961. Min Act: -0.1700
Data Index: 4781169 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7802. Min Act: -0.1700
Data Index: 3863791 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.8121. Min Act: -0.1700
Data Index: 136200 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7802. Min Act: -0.1700
Data Index: 5079323 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7802. Min Act: -0.1700
Data Index: 8769138 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7802. Min Act: -0.1700
Data Index: 3600505 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7643. Min Act: -0.1700
Data Index: 5711053 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7643. Min Act: -0.1700
Data Index: 4049762 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7643. Min Act: -0.1700
Data Index: 7288055 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7643. Min Act: -0.1700
Data Index: 7038901 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7643. Min Act: -0.1700
Data Index: 4490242 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7323. Min Act: -0.1700
Data Index: 3515365 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7483. Min Act: -0.1700
Data Index: 2628939 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7483. Min Act: -0.1700
Data Index: 86966 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7483. Min Act: -0.1700
Data Index: 2940038 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8598. Min Range: -2.8598
Max Act: 2.7643. Min Act: -0.1700
Data Index: 2992707 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19