Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5857 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0751. Min Range: -10.0751
Max Act: 10.0751. Min Act: -0.1700
Data Index: 1921453 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.8876. Min Act: -0.1700
Data Index: 1742528 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.7001. Min Act: -0.1700
Data Index: 5658605 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.4501. Min Act: -0.1700
Data Index: 3244634 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.4501. Min Act: -0.1700
Data Index: 3140069 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.4501. Min Act: -0.1700
Data Index: 834029 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.4501. Min Act: -0.1700
Data Index: 1681596 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.3876. Min Act: -0.1700
Data Index: 2339543 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.3876. Min Act: -0.1700
Data Index: 5291481 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2626. Min Act: -0.1700
Data Index: 6834428 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.3251. Min Act: -0.1700
Data Index: 6085779 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2626. Min Act: -0.1700
Data Index: 3921121 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2626. Min Act: -0.1700
Data Index: 5850163 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.3251. Min Act: -0.1700
Data Index: 3329130 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2001. Min Act: -0.1700
Data Index: 2602488 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2001. Min Act: -0.1700
Data Index: 4578186 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2001. Min Act: -0.1700
Data Index: 6071381 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2001. Min Act: -0.1700
Data Index: 6984757 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.1376. Min Act: -0.1700
Data Index: 3349767 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0751. Min Range: -10.0751
Max Act: 9.2001. Min Act: -0.1700
Data Index: 574751 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19