Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.6551. Min Act: -0.1699
Data Index: 1314890 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.6311. Min Act: -0.1700
Data Index: 4103939 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.6231. Min Act: -0.1697
Data Index: 5201392 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.6073. Min Act: -0.1700
Data Index: 4066146 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.6152. Min Act: -0.1690
Data Index: 929927 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.6073. Min Act: -0.1700
Data Index: 5954677 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5994. Min Act: -0.1700
Data Index: 2597137 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5837. Min Act: -0.1699
Data Index: 179550 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5837. Min Act: -0.1685
Data Index: 3120169 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5681. Min Act: -0.1696
Data Index: 6419308 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5681. Min Act: -0.1700
Data Index: 1727773 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5681. Min Act: -0.1700
Data Index: 3441213 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5681. Min Act: -0.1692
Data Index: 5434917 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5681. Min Act: -0.1700
Data Index: 5159553 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5604. Min Act: -0.1696
Data Index: 2103229 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5527. Min Act: -0.1700
Data Index: 5916628 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5604. Min Act: -0.1700
Data Index: 4992438 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5527. Min Act: -0.1700
Data Index: 270542 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5527. Min Act: -0.1698
Data Index: 3298264 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6551. Min Range: -0.6551
Max Act: 0.5527. Min Act: -0.1700
Data Index: 2323341 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19