Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.8815. Min Act: -0.1700
Data Index: 3282230 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.7253. Min Act: -0.1700
Data Index: 8825447 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.5690. Min Act: -0.1700
Data Index: 7094669 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.4128. Min Act: -0.1700
Data Index: 2470926 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.3503. Min Act: -0.1700
Data Index: 6549014 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.3503. Min Act: -0.1700
Data Index: 8017902 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.2565. Min Act: -0.1700
Data Index: 3953119 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.2253. Min Act: -0.1700
Data Index: 6666072 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.2565. Min Act: -0.1700
Data Index: 1178441 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.1940. Min Act: -0.1700
Data Index: 1298947 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.1940. Min Act: -0.1700
Data Index: 435364 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.1315. Min Act: -0.1700
Data Index: 7625400 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5606868 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.1628. Min Act: -0.1700
Data Index: 5545212 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.0690. Min Act: -0.1700
Data Index: 5344583 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.0690. Min Act: -0.1700
Data Index: 4914749 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.0690. Min Act: -0.1700
Data Index: 7003938 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.0690. Min Act: -0.1700
Data Index: 2561514 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.0690. Min Act: -0.1700
Data Index: 7112248 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8815. Min Range: -6.8815
Max Act: 6.0378. Min Act: -0.1700
Data Index: 5019736 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19