Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2911 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.3698. Min Act: -0.1700
Data Index: 589221 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.3698. Min Act: -0.1700
Data Index: 5267297 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.3386. Min Act: -0.1700
Data Index: 3178244 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.3386. Min Act: -0.1700
Data Index: 852267 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.3073. Min Act: -0.1700
Data Index: 6037799 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2448. Min Act: -0.1700
Data Index: 3377066 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2761. Min Act: -0.1700
Data Index: 8401975 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2448. Min Act: -0.1700
Data Index: 7191027 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2448. Min Act: -0.1700
Data Index: 2670074 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2448. Min Act: -0.1700
Data Index: 1762809 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.1823. Min Act: -0.1700
Data Index: 7293148 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2136. Min Act: -0.1700
Data Index: 3564733 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2136. Min Act: -0.1700
Data Index: 5669227 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2136. Min Act: -0.1700
Data Index: 4989337 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2136. Min Act: -0.1700
Data Index: 7906925 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2136. Min Act: -0.1700
Data Index: 7640399 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.2136. Min Act: -0.1700
Data Index: 3957892 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.1823. Min Act: -0.1700
Data Index: 273732 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.1823. Min Act: -0.1700
Data Index: 5140706 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3698. Min Range: -5.3698
Max Act: 5.1823. Min Act: -0.1700
Data Index: 3142198 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19