Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6866. Min Range: -8.6866
Max Act: 8.6866. Min Act: -0.1700
Data Index: 4704664 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6866. Min Range: -8.6866
Max Act: 8.2491. Min Act: -0.1700
Data Index: 8004309 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6866. Min Range: -8.6866
Max Act: 8.1866. Min Act: -0.1700
Data Index: 8501947 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6866. Min Range: -8.6866
Max Act: 8.0304. Min Act: -0.1700
Data Index: 7276641 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.9366. Min Act: -0.1700
Data Index: 907918 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.8429. Min Act: -0.1700
Data Index: 3964577 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.8116. Min Act: -0.1700
Data Index: 8085534 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.7804. Min Act: -0.1700
Data Index: 6423427 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.8116. Min Act: -0.1700
Data Index: 3459064 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.7804. Min Act: -0.1700
Data Index: 330338 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.7491. Min Act: -0.1700
Data Index: 2584951 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.7491. Min Act: -0.1700
Data Index: 725782 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.7179. Min Act: -0.1700
Data Index: 3714859 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6866. Min Act: -0.1700
Data Index: 7883828 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6866. Min Act: -0.1700
Data Index: 1493148 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6866. Min Act: -0.1700
Data Index: 524224 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6554. Min Act: -0.1700
Data Index: 3922925 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6554. Min Act: -0.1700
Data Index: 4124464 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6554. Min Act: -0.1700
Data Index: 1910807 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6866. Min Range: -8.6866
Max Act: 7.6554. Min Act: -0.1700
Data Index: 6370579 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19