Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5349 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.4284. Min Act: -0.1700
Data Index: 2654223 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.3659. Min Act: -0.1700
Data Index: 5645082 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.3346. Min Act: -0.1700
Data Index: 1419439 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.2409. Min Act: -0.1700
Data Index: 5446857 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.2409. Min Act: -0.1700
Data Index: 2654216 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.2096. Min Act: -0.1700
Data Index: 2611115 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.1784. Min Act: -0.1700
Data Index: 3676015 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.1471. Min Act: -0.1700
Data Index: 4358761 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.1159. Min Act: -0.1700
Data Index: 1368352 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.0846. Min Act: -0.1700
Data Index: 2144957 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.0534. Min Act: -0.1700
Data Index: 5628941 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.0221. Min Act: -0.1700
Data Index: 8275732 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.0221. Min Act: -0.1700
Data Index: 3444723 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 3422295 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 6135348 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 3019436 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 2627987 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 8798236 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 7843586 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9596. Min Act: -0.1700
Data Index: 7641657 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19