Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1030 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2198. Min Range: -5.2198
Max Act: 5.2198. Min Act: -0.1700
Data Index: 2179496 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2198. Min Range: -5.2198
Max Act: 5.1573. Min Act: -0.1700
Data Index: 2701505 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2198. Min Range: -5.2198
Max Act: 5.0636. Min Act: -0.1700
Data Index: 4324123 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2198. Min Range: -5.2198
Max Act: 5.0323. Min Act: -0.1700
Data Index: 8125887 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2198. Min Range: -5.2198
Max Act: 5.0323. Min Act: -0.1700
Data Index: 8125892 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9698. Min Act: -0.1700
Data Index: 7895386 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2198. Min Range: -5.2198
Max Act: 5.0011. Min Act: -0.1700
Data Index: 7379826 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9698. Min Act: -0.1700
Data Index: 5361940 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9698. Min Act: -0.1700
Data Index: 811074 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9698. Min Act: -0.1700
Data Index: 6670899 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9698. Min Act: -0.1700
Data Index: 1011777 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 2246171 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 910099 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 1797308 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 1300164 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 8245806 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 6655421 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9386. Min Act: -0.1700
Data Index: 6385719 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9073. Min Act: -0.1700
Data Index: 3089221 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2198. Min Range: -5.2198
Max Act: 4.9073. Min Act: -0.1700
Data Index: 7717482 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19