Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.5837. Min Act: -0.1700
Data Index: 807369 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.4274. Min Act: -0.1700
Data Index: 7905829 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.3649. Min Act: -0.1700
Data Index: 7159412 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.2712. Min Act: -0.1700
Data Index: 7752367 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.1149. Min Act: -0.1700
Data Index: 6036808 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.0837. Min Act: -0.1700
Data Index: 2076015 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.0524. Min Act: -0.1700
Data Index: 634667 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.0212. Min Act: -0.1700
Data Index: 4851870 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5837. Min Range: -6.5837
Max Act: 6.0212. Min Act: -0.1700
Data Index: 4105089 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.9899. Min Act: -0.1700
Data Index: 8558815 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.9587. Min Act: -0.1700
Data Index: 1873800 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.9587. Min Act: -0.1700
Data Index: 1104316 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.9274. Min Act: -0.1700
Data Index: 2007755 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.9274. Min Act: -0.1700
Data Index: 3571825 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.9274. Min Act: -0.1700
Data Index: 8010151 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.8962. Min Act: -0.1700
Data Index: 3650148 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.8649. Min Act: -0.1700
Data Index: 2076006 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.8962. Min Act: -0.1700
Data Index: 953103 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.8962. Min Act: -0.1700
Data Index: 7721277 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5837. Min Range: -6.5837
Max Act: 5.8962. Min Act: -0.1700
Data Index: 6793436 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19