Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5464 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.1252. Min Act: -0.1700
Data Index: 1874641 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0939. Min Act: -0.1700
Data Index: 7595434 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0939. Min Act: -0.1700
Data Index: 2350507 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0939. Min Act: -0.1700
Data Index: 8256504 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0939. Min Act: -0.1700
Data Index: 6503779 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0939. Min Act: -0.1700
Data Index: 4541377 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0627. Min Act: -0.1700
Data Index: 1222301 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0627. Min Act: -0.1700
Data Index: 6583940 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0002. Min Act: -0.1700
Data Index: 4650240 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9689. Min Act: -0.1700
Data Index: 4829739 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9689. Min Act: -0.1700
Data Index: 8777060 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9689. Min Act: -0.1700
Data Index: 8289577 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9689. Min Act: -0.1700
Data Index: 2542160 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1252. Min Range: -5.1252
Max Act: 5.0002. Min Act: -0.1700
Data Index: 2075693 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9377. Min Act: -0.1700
Data Index: 7910423 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9064. Min Act: -0.1700
Data Index: 2981026 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9064. Min Act: -0.1700
Data Index: 6874682 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9064. Min Act: -0.1700
Data Index: 7418961 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9064. Min Act: -0.1700
Data Index: 7801595 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1252. Min Range: -5.1252
Max Act: 4.9064. Min Act: -0.1700
Data Index: 289337 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19