Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.8466. Min Act: -0.1700
Data Index: 6295256 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.7528. Min Act: -0.1700
Data Index: 7495489 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.3778. Min Act: -0.1700
Data Index: 7499135 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.3778. Min Act: -0.1700
Data Index: 7754981 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.2216. Min Act: -0.1700
Data Index: 3888666 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.1278. Min Act: -0.1700
Data Index: 4274514 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.0966. Min Act: -0.1700
Data Index: 3206730 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.0653. Min Act: -0.1700
Data Index: 1326280 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.0341. Min Act: -0.1700
Data Index: 8710048 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.0028. Min Act: -0.1700
Data Index: 286739 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.0028. Min Act: -0.1700
Data Index: 5804336 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8466. Min Range: -7.8466
Max Act: 7.0028. Min Act: -0.1700
Data Index: 6572636 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.9716. Min Act: -0.1700
Data Index: 4051741 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.9403. Min Act: -0.1700
Data Index: 8282299 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.9403. Min Act: -0.1700
Data Index: 7556247 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.9403. Min Act: -0.1700
Data Index: 6645400 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.8778. Min Act: -0.1700
Data Index: 574299 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.8778. Min Act: -0.1700
Data Index: 2281202 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.8778. Min Act: -0.1700
Data Index: 5584406 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8466. Min Range: -7.8466
Max Act: 6.8153. Min Act: -0.1700
Data Index: 557498 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19