Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6305 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0906. Min Range: -6.0906
Max Act: 6.0906. Min Act: -0.1700
Data Index: 2860133 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9969. Min Act: -0.1700
Data Index: 2456797 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9344. Min Act: -0.1700
Data Index: 2224699 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9344. Min Act: -0.1700
Data Index: 1158533 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9344. Min Act: -0.1700
Data Index: 8112284 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9031. Min Act: -0.1700
Data Index: 406338 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9031. Min Act: -0.1700
Data Index: 4248724 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.9031. Min Act: -0.1700
Data Index: 2593180 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.8719. Min Act: -0.1700
Data Index: 33674 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.8406. Min Act: -0.1700
Data Index: 5233003 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.8094. Min Act: -0.1700
Data Index: 5925360 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.7781. Min Act: -0.1700
Data Index: 2235938 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.7781. Min Act: -0.1700
Data Index: 3160289 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.7781. Min Act: -0.1700
Data Index: 6628986 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.7156. Min Act: -0.1700
Data Index: 4874831 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.7156. Min Act: -0.1700
Data Index: 1465797 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.7156. Min Act: -0.1700
Data Index: 790992 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.6844. Min Act: -0.1700
Data Index: 2500958 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.6844. Min Act: -0.1700
Data Index: 6345993 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0906. Min Range: -6.0906
Max Act: 5.6844. Min Act: -0.1700
Data Index: 5810698 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19