Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2199. Min Range: -6.2199
Max Act: 6.2199. Min Act: -0.1700
Data Index: 5352802 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2199. Min Range: -6.2199
Max Act: 6.2199. Min Act: -0.1700
Data Index: 3434598 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2199. Min Range: -6.2199
Max Act: 6.1574. Min Act: -0.1700
Data Index: 3144929 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.9699. Min Act: -0.1700
Data Index: 6005624 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.9387. Min Act: -0.1700
Data Index: 8646168 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.9387. Min Act: -0.1700
Data Index: 8016218 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.9074. Min Act: -0.1700
Data Index: 2818041 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8762. Min Act: -0.1700
Data Index: 5739854 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8449. Min Act: -0.1700
Data Index: 8654955 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8449. Min Act: -0.1700
Data Index: 8222860 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8449. Min Act: -0.1700
Data Index: 2949121 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8137. Min Act: -0.1700
Data Index: 390276 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8137. Min Act: -0.1700
Data Index: 4616616 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8137. Min Act: -0.1700
Data Index: 3311777 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.8137. Min Act: -0.1700
Data Index: 853588 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.7824. Min Act: -0.1700
Data Index: 4829700 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.7512. Min Act: -0.1700
Data Index: 1238640 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.7512. Min Act: -0.1700
Data Index: 4203422 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.7512. Min Act: -0.1700
Data Index: 4138684 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2199. Min Range: -6.2199
Max Act: 5.7512. Min Act: -0.1700
Data Index: 3904810 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19