Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.8396. Min Act: -0.1700
Data Index: 5897860 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.8083. Min Act: -0.1700
Data Index: 2605043 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.7771. Min Act: -0.1700
Data Index: 2158008 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.7771. Min Act: -0.1700
Data Index: 1885433 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.7146. Min Act: -0.1700
Data Index: 8816203 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.7146. Min Act: -0.1700
Data Index: 5269945 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.7146. Min Act: -0.1700
Data Index: 8086364 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.7146. Min Act: -0.1700
Data Index: 4613742 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.6833. Min Act: -0.1700
Data Index: 994880 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.6521. Min Act: -0.1700
Data Index: 2786614 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.6521. Min Act: -0.1700
Data Index: 8132821 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.6208. Min Act: -0.1700
Data Index: 4868614 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.6208. Min Act: -0.1700
Data Index: 2913760 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5896. Min Act: -0.1700
Data Index: 6484365 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5896. Min Act: -0.1700
Data Index: 5584060 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5896. Min Act: -0.1700
Data Index: 246002 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5583. Min Act: -0.1700
Data Index: 6944420 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5583. Min Act: -0.1700
Data Index: 3052186 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5583. Min Act: -0.1700
Data Index: 699547 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8396. Min Range: -4.8396
Max Act: 4.5583. Min Act: -0.1700
Data Index: 7280306 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19