Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4200 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.7715. Min Act: -0.1700
Data Index: 90764 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.7403. Min Act: -0.1700
Data Index: 228868 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.7403. Min Act: -0.1700
Data Index: 3131380 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6778. Min Act: -0.1700
Data Index: 2987665 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6465. Min Act: -0.1700
Data Index: 4496442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6153. Min Act: -0.1700
Data Index: 2445390 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6153. Min Act: -0.1700
Data Index: 5988727 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6153. Min Act: -0.1700
Data Index: 7774170 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 2609930 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6153. Min Act: -0.1700
Data Index: 8553887 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 4709963 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.6153. Min Act: -0.1700
Data Index: 1088852 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 2038948 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5528. Min Act: -0.1700
Data Index: 5776270 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1677
Data Index: 2717885 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 2656922 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 234201 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 6440478 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 3297253 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7715. Min Range: -5.7715
Max Act: 5.5840. Min Act: -0.1700
Data Index: 1254569 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19