Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.9139. Min Act: -0.1700
Data Index: 5078093 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.9139. Min Act: -0.1698
Data Index: 4566250 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 7115989 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 2900728 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.7889. Min Act: -0.1698
Data Index: 4797367 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 1152083 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 1142160 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 4410829 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 2922328 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 5890904 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 2725369 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 5551944 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 7047317 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 6192984 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.8514. Min Act: -0.1700
Data Index: 429722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.7889. Min Act: -0.1700
Data Index: 2734059 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.7889. Min Act: -0.1700
Data Index: 2415815 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.7889. Min Act: -0.1699
Data Index: 3241406 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.7889. Min Act: -0.1700
Data Index: 108979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9139. Min Range: -7.9139
Max Act: 7.7264. Min Act: -0.1700
Data Index: 4532547 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19