Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2199. Min Range: -7.2199
Max Act: 7.2199. Min Act: -0.1700
Data Index: 5517972 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.9387. Min Act: -0.1700
Data Index: 5171070 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.9387. Min Act: -0.1700
Data Index: 5305329 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.8762. Min Act: -0.1700
Data Index: 1862700 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.8137. Min Act: -0.1700
Data Index: 1363970 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.7512. Min Act: -0.1700
Data Index: 3015253 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.7199. Min Act: -0.1700
Data Index: 5305328 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6887. Min Act: -0.1700
Data Index: 8615163 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6574. Min Act: -0.1700
Data Index: 1946768 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6574. Min Act: -0.1700
Data Index: 7629396 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6574. Min Act: -0.1700
Data Index: 5862568 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6262. Min Act: -0.1700
Data Index: 5646956 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.5949. Min Act: -0.1700
Data Index: 2194276 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6262. Min Act: -0.1700
Data Index: 7289505 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.5949. Min Act: -0.1700
Data Index: 6270884 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6262. Min Act: -0.1700
Data Index: 1835891 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.5949. Min Act: -0.1700
Data Index: 1759961 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.6262. Min Act: -0.1700
Data Index: 6428262 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.5949. Min Act: -0.1700
Data Index: 3072433 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2199. Min Range: -7.2199
Max Act: 6.5637. Min Act: -0.1700
Data Index: 2016668 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19