Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.9985. Min Act: -0.1700
Data Index: 3519323 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.9673. Min Act: -0.1700
Data Index: 7968898 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.9673. Min Act: -0.1700
Data Index: 7968916 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.9673. Min Act: -0.1700
Data Index: 3771622 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.9360. Min Act: -0.1700
Data Index: 3694271 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.8423. Min Act: -0.1700
Data Index: 1123082 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.8110. Min Act: -0.1700
Data Index: 184589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.7798. Min Act: -0.1700
Data Index: 4326185 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.5923. Min Act: -0.1700
Data Index: 7765878 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.6235. Min Act: -0.1700
Data Index: 895802 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.5923. Min Act: -0.1700
Data Index: 1323746 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.5610. Min Act: -0.1700
Data Index: 4647114 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.5610. Min Act: -0.1700
Data Index: 8609858 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4985. Min Act: -0.1700
Data Index: 184441 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4985. Min Act: -0.1700
Data Index: 1364810 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4985. Min Act: -0.1700
Data Index: 1397467 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4673. Min Act: -0.1700
Data Index: 6757174 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4360. Min Act: -0.1700
Data Index: 6723885 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4673. Min Act: -0.1700
Data Index: 7077949 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9985. Min Range: -4.9985
Max Act: 4.4673. Min Act: -0.1700
Data Index: 6402397 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19