Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1620. Min Range: -4.1620
Max Act: 4.1620. Min Act: -0.1700
Data Index: 1068442 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1620. Min Range: -4.1620
Max Act: 4.0995. Min Act: -0.1700
Data Index: 177964 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1620. Min Range: -4.1620
Max Act: 4.0370. Min Act: -0.1700
Data Index: 3078887 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1620. Min Range: -4.1620
Max Act: 4.0370. Min Act: -0.1700
Data Index: 5527404 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1620. Min Range: -4.1620
Max Act: 4.0057. Min Act: -0.1700
Data Index: 5014916 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1620. Min Range: -4.1620
Max Act: 4.0057. Min Act: -0.1700
Data Index: 6318163 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.9745. Min Act: -0.1700
Data Index: 4417967 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.9588. Min Act: -0.1700
Data Index: 7584016 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8963. Min Act: -0.1700
Data Index: 8473969 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8807. Min Act: -0.1700
Data Index: 1453761 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8963. Min Act: -0.1700
Data Index: 7837689 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8963. Min Act: -0.1700
Data Index: 7524828 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8807. Min Act: -0.1700
Data Index: 208015 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8650. Min Act: -0.1700
Data Index: 1683072 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8650. Min Act: -0.1700
Data Index: 485201 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8650. Min Act: -0.1700
Data Index: 338679 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8494. Min Act: -0.1700
Data Index: 6292336 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8494. Min Act: -0.1700
Data Index: 118647 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8338. Min Act: -0.1700
Data Index: 3614851 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1620. Min Range: -4.1620
Max Act: 3.8025. Min Act: -0.1700
Data Index: 8051502 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19