Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3454. Min Range: -6.3454
Max Act: 6.3454. Min Act: -0.1700
Data Index: 4903922 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3454. Min Range: -6.3454
Max Act: 6.2517. Min Act: -0.1700
Data Index: 3870767 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3454. Min Range: -6.3454
Max Act: 6.1892. Min Act: -0.1700
Data Index: 839007 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3454. Min Range: -6.3454
Max Act: 6.0954. Min Act: -0.1700
Data Index: 4061204 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.9704. Min Act: -0.1700
Data Index: 2698618 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.9392. Min Act: -0.1700
Data Index: 4522743 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.9392. Min Act: -0.1700
Data Index: 4765420 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.9079. Min Act: -0.1700
Data Index: 5340322 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.8454. Min Act: -0.1700
Data Index: 3110924 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.8454. Min Act: -0.1700
Data Index: 7920060 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.7517. Min Act: -0.1700
Data Index: 5262136 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.7829. Min Act: -0.1700
Data Index: 2217439 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 732790 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 4333181 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 4449832 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.6579. Min Act: -0.1700
Data Index: 2817966 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.5642. Min Act: -0.1700
Data Index: 1070468 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.6267. Min Act: -0.1700
Data Index: 3243645 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.5642. Min Act: -0.1700
Data Index: 4856967 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3454. Min Range: -6.3454
Max Act: 5.5642. Min Act: -0.1700
Data Index: 5384579 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19