Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1027. Min Range: -7.1027
Max Act: 7.1027. Min Act: -0.1700
Data Index: 314518 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1027. Min Range: -7.1027
Max Act: 7.0402. Min Act: -0.1699
Data Index: 2238414 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.9464. Min Act: -0.1700
Data Index: 7708896 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.9464. Min Act: -0.1700
Data Index: 552714 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.9464. Min Act: -0.1700
Data Index: 7358537 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.9152. Min Act: -0.1700
Data Index: 7439970 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.9152. Min Act: -0.1700
Data Index: 3221372 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8839. Min Act: -0.1700
Data Index: 8321381 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8839. Min Act: -0.1700
Data Index: 4355615 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8527. Min Act: -0.1700
Data Index: 1848637 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8527. Min Act: -0.1700
Data Index: 7053520 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8214. Min Act: -0.1700
Data Index: 8164580 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8214. Min Act: -0.1700
Data Index: 7152977 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.7902. Min Act: -0.1700
Data Index: 6636552 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.8214. Min Act: -0.1700
Data Index: 6228317 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.7589. Min Act: -0.1700
Data Index: 2490649 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.7589. Min Act: -0.1700
Data Index: 4241142 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.7277. Min Act: -0.1700
Data Index: 2791415 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.7277. Min Act: -0.1700
Data Index: 1303199 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1027. Min Range: -7.1027
Max Act: 6.7589. Min Act: -0.1700
Data Index: 6741754 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19