Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6350 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.2078. Min Act: -0.1700
Data Index: 4626523 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2078. Min Range: -6.2078
Max Act: 6.0828. Min Act: -0.1700
Data Index: 8481763 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9578. Min Act: -0.1700
Data Index: 6704835 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9578. Min Act: -0.1700
Data Index: 7201410 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9578. Min Act: -0.1700
Data Index: 2094563 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8953. Min Act: -0.1700
Data Index: 1992978 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.9265. Min Act: -0.1700
Data Index: 1986152 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8640. Min Act: -0.1700
Data Index: 161181 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8953. Min Act: -0.1700
Data Index: 7716919 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8640. Min Act: -0.1700
Data Index: 4830341 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8640. Min Act: -0.1700
Data Index: 2150083 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8328. Min Act: -0.1700
Data Index: 4058946 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8640. Min Act: -0.1700
Data Index: 6357911 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8640. Min Act: -0.1700
Data Index: 336304 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8328. Min Act: -0.1700
Data Index: 3073313 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8328. Min Act: -0.1700
Data Index: 6695745 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8640. Min Act: -0.1700
Data Index: 349622 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 4651797 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 1479451 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2078. Min Range: -6.2078
Max Act: 5.8015. Min Act: -0.1700
Data Index: 2469900 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19