Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5169 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0975. Min Range: -3.0975
Max Act: 3.0975. Min Act: -0.1507
Data Index: 6415377 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0975. Min Range: -3.0975
Max Act: 3.0028. Min Act: -0.1700
Data Index: 4365592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0975. Min Range: -3.0975
Max Act: 3.0028. Min Act: -0.1692
Data Index: 302367 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0975. Min Range: -3.0975
Max Act: 3.0028. Min Act: -0.1699
Data Index: 6108634 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.9395. Min Act: -0.1686
Data Index: 1538724 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.9078. Min Act: -0.1697
Data Index: 3205123 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.9078. Min Act: -0.1673
Data Index: 7454973 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8761. Min Act: -0.1700
Data Index: 22274 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8602. Min Act: -0.1688
Data Index: 2621303 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8602. Min Act: -0.1669
Data Index: 759677 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8602. Min Act: -0.1700
Data Index: 7244799 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8443. Min Act: -0.1700
Data Index: 6837508 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8284. Min Act: -0.1700
Data Index: 2000033 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8284. Min Act: -0.1698
Data Index: 6060153 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.8125. Min Act: -0.1700
Data Index: 8378870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.7966. Min Act: -0.1682
Data Index: 3204893 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.7807. Min Act: -0.1699
Data Index: 2066858 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.7807. Min Act: -0.1696
Data Index: 7263417 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.7807. Min Act: -0.1697
Data Index: 763774 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0975. Min Range: -3.0975
Max Act: 2.7807. Min Act: -0.1635
Data Index: 2951835 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19