Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5773 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9809. Min Act: -0.1700
Data Index: 4408736 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0121. Min Range: -6.0121
Max Act: 6.0121. Min Act: -0.1700
Data Index: 8253728 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9809. Min Act: -0.1700
Data Index: 1492342 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9809. Min Act: -0.1700
Data Index: 4559781 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9496. Min Act: -0.1700
Data Index: 428212 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9496. Min Act: -0.1700
Data Index: 1523836 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9184. Min Act: -0.1700
Data Index: 6442411 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.9184. Min Act: -0.1700
Data Index: 2747295 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.8871. Min Act: -0.1700
Data Index: 6642439 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.8246. Min Act: -0.1700
Data Index: 815371 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.8246. Min Act: -0.1700
Data Index: 1960791 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.8246. Min Act: -0.1700
Data Index: 3666684 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7934. Min Act: -0.1700
Data Index: 6274803 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7934. Min Act: -0.1700
Data Index: 20764 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7934. Min Act: -0.1700
Data Index: 7441966 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7934. Min Act: -0.1700
Data Index: 3191538 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7934. Min Act: -0.1700
Data Index: 3465009 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7621. Min Act: -0.1700
Data Index: 2448829 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7621. Min Act: -0.1700
Data Index: 3897573 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0121. Min Range: -6.0121
Max Act: 5.7309. Min Act: -0.1700
Data Index: 3219917 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19