Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5907 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0164. Min Range: -8.0164
Max Act: 8.0164. Min Act: -0.1700
Data Index: 1364704 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.8914. Min Act: -0.1700
Data Index: 3106272 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.7977. Min Act: -0.1700
Data Index: 6743808 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.7977. Min Act: -0.1700
Data Index: 526641 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.7039. Min Act: -0.1700
Data Index: 1205163 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.7039. Min Act: -0.1700
Data Index: 4758363 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.6727. Min Act: -0.1700
Data Index: 6959878 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.6102. Min Act: -0.1700
Data Index: 7869895 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.6102. Min Act: -0.1700
Data Index: 2103244 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5789. Min Act: -0.1700
Data Index: 7498351 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5164. Min Act: -0.1700
Data Index: 2474125 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5164. Min Act: -0.1700
Data Index: 7014808 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5477. Min Act: -0.1700
Data Index: 5388660 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5164. Min Act: -0.1700
Data Index: 6355999 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5477. Min Act: -0.1700
Data Index: 5636946 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.4852. Min Act: -0.1700
Data Index: 5055153 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.5164. Min Act: -0.1700
Data Index: 2236110 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.4539. Min Act: -0.1700
Data Index: 8487961 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.4539. Min Act: -0.1700
Data Index: 6410939 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0164. Min Range: -8.0164
Max Act: 7.4852. Min Act: -0.1700
Data Index: 5786016 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19