Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5692 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2913. Min Range: -6.2913
Max Act: 6.2913. Min Act: -0.1700
Data Index: 6002279 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2913. Min Range: -6.2913
Max Act: 6.1351. Min Act: -0.1700
Data Index: 3189749 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2913. Min Range: -6.2913
Max Act: 6.0413. Min Act: -0.1700
Data Index: 8467569 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2913. Min Range: -6.2913
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3721694 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2913. Min Range: -6.2913
Max Act: 6.0413. Min Act: -0.1700
Data Index: 4388705 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2913. Min Range: -6.2913
Max Act: 6.0101. Min Act: -0.1700
Data Index: 2546278 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.8851. Min Act: -0.1700
Data Index: 4713664 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.8851. Min Act: -0.1700
Data Index: 7612388 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.8538. Min Act: -0.1700
Data Index: 4643758 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.8538. Min Act: -0.1700
Data Index: 6762717 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.8538. Min Act: -0.1700
Data Index: 3804854 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.8538. Min Act: -0.1700
Data Index: 1558352 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7913. Min Act: -0.1700
Data Index: 376186 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7601. Min Act: -0.1700
Data Index: 2648379 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7601. Min Act: -0.1700
Data Index: 7070179 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7288. Min Act: -0.1700
Data Index: 2239395 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.6976. Min Act: -0.1700
Data Index: 5346339 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7288. Min Act: -0.1700
Data Index: 5966378 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7288. Min Act: -0.1700
Data Index: 3083505 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2913. Min Range: -6.2913
Max Act: 5.7288. Min Act: -0.1700
Data Index: 431379 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19