Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.2343. Min Act: -0.1700
Data Index: 3814509 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.2031. Min Act: -0.1700
Data Index: 6487980 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.1093. Min Act: -0.1700
Data Index: 3744669 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0781. Min Act: -0.1700
Data Index: 7195264 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.1093. Min Act: -0.1700
Data Index: 4761931 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0468. Min Act: -0.1700
Data Index: 4258302 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0468. Min Act: -0.1700
Data Index: 3425440 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0468. Min Act: -0.1700
Data Index: 3064745 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0468. Min Act: -0.1700
Data Index: 3270139 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0156. Min Act: -0.1700
Data Index: 2143062 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0156. Min Act: -0.1700
Data Index: 4818044 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0468. Min Act: -0.1700
Data Index: 6296472 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9531. Min Act: -0.1700
Data Index: 5064205 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2343. Min Range: -6.2343
Max Act: 6.0156. Min Act: -0.1700
Data Index: 2972690 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 156578 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 3824264 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 2967645 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 925254 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9843. Min Act: -0.1700
Data Index: 3130570 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2343. Min Range: -6.2343
Max Act: 5.9531. Min Act: -0.1700
Data Index: 3863666 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19