Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.9936. Min Act: -0.1700
Data Index: 6933010 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.8061. Min Act: -0.1700
Data Index: 8069113 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.7749. Min Act: -0.1700
Data Index: 6973755 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.7749. Min Act: -0.1700
Data Index: 2791369 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.6499. Min Act: -0.1700
Data Index: 3308747 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.6186. Min Act: -0.1700
Data Index: 4173942 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.5249. Min Act: -0.1700
Data Index: 5424908 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.5249. Min Act: -0.1700
Data Index: 794565 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.5249. Min Act: -0.1700
Data Index: 5337581 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.4936. Min Act: -0.1700
Data Index: 1153897 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.5249. Min Act: -0.1700
Data Index: 7562218 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.4624. Min Act: -0.1700
Data Index: 7744158 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.4936. Min Act: -0.1700
Data Index: 8155345 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3999. Min Act: -0.1700
Data Index: 4185325 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3999. Min Act: -0.1700
Data Index: 261393 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3999. Min Act: -0.1700
Data Index: 5399996 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3686. Min Act: -0.1700
Data Index: 4759108 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3686. Min Act: -0.1700
Data Index: 7423980 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3999. Min Act: -0.1700
Data Index: 7774847 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9936. Min Range: -6.9936
Max Act: 6.3374. Min Act: -0.1700
Data Index: 7759111 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19