Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4444 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.1115. Min Act: -0.1700
Data Index: 619387 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0780. Min Act: -0.1700
Data Index: 5092637 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0780. Min Act: -0.1700
Data Index: 1147341 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0780. Min Act: -0.1700
Data Index: 5915181 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0612. Min Act: -0.1700
Data Index: 989543 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0612. Min Act: -0.1700
Data Index: 5043242 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0275. Min Act: -0.1700
Data Index: 3709709 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0612. Min Act: -0.1700
Data Index: 5402664 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0444. Min Act: -0.1700
Data Index: 2926073 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0444. Min Act: -0.1700
Data Index: 8722529 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0444. Min Act: -0.1700
Data Index: 1063044 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0275. Min Act: -0.1700
Data Index: 131483 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0444. Min Act: -0.1700
Data Index: 5447111 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0107. Min Act: -0.1700
Data Index: 3770778 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0275. Min Act: -0.1700
Data Index: 3412691 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0107. Min Act: -0.1700
Data Index: 4200820 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0107. Min Act: -0.1700
Data Index: 7013069 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1115. Min Range: -2.1115
Max Act: 1.9938. Min Act: -0.1700
Data Index: 7066372 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1115. Min Range: -2.1115
Max Act: 2.0107. Min Act: -0.1699
Data Index: 3591010 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1115. Min Range: -2.1115
Max Act: 1.9938. Min Act: -0.1700
Data Index: 3591018 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19