Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.7087. Min Act: -0.1700
Data Index: 4229371 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7087. Min Range: -5.7087
Max Act: 5.1149. Min Act: -0.1700
Data Index: 6251024 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.9899. Min Act: -0.1699
Data Index: 4413696 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 5458360 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.9587. Min Act: -0.1700
Data Index: 7592528 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8962. Min Act: -0.1700
Data Index: 150259 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.9274. Min Act: -0.1700
Data Index: 7292151 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8962. Min Act: -0.1700
Data Index: 5298520 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8962. Min Act: -0.1700
Data Index: 1842771 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8649. Min Act: -0.1700
Data Index: 7910442 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1431687 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8337. Min Act: -0.1700
Data Index: 7238062 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8337. Min Act: -0.1700
Data Index: 6320903 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8024. Min Act: -0.1700
Data Index: 8146392 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8024. Min Act: -0.1700
Data Index: 6847883 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8024. Min Act: -0.1700
Data Index: 649300 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.8024. Min Act: -0.1700
Data Index: 5258439 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.7712. Min Act: -0.1700
Data Index: 6749417 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.7712. Min Act: -0.1700
Data Index: 2899368 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7087. Min Range: -5.7087
Max Act: 4.7712. Min Act: -0.1700
Data Index: 791213 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19