Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.8027. Min Act: -0.1700
Data Index: 1489076 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3340. Min Act: -0.1700
Data Index: 7414942 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3027. Min Act: -0.1700
Data Index: 3468324 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.2090. Min Act: -0.1700
Data Index: 2113243 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.1465. Min Act: -0.1700
Data Index: 4617413 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.9902. Min Act: -0.1700
Data Index: 1505002 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.9590. Min Act: -0.1700
Data Index: 7030546 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.9277. Min Act: -0.1700
Data Index: 4069699 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.9277. Min Act: -0.1700
Data Index: 1375101 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8652. Min Act: -0.1700
Data Index: 2275768 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8965. Min Act: -0.1700
Data Index: 54726 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8652. Min Act: -0.1700
Data Index: 8739659 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8652. Min Act: -0.1700
Data Index: 1983197 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8652. Min Act: -0.1700
Data Index: 2622532 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8652. Min Act: -0.1700
Data Index: 8163271 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8340. Min Act: -0.1700
Data Index: 5223578 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8340. Min Act: -0.1700
Data Index: 1229950 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8340. Min Act: -0.1700
Data Index: 4706681 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8340. Min Act: -0.1700
Data Index: 1995683 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8027. Min Range: -5.8027
Max Act: 4.8340. Min Act: -0.1700
Data Index: 8228074 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19