Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.0524. Min Range: -14.0524
Max Act: 14.0524. Min Act: -0.1700
Data Index: 3361446 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.4899. Min Act: -0.1700
Data Index: 3075552 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.4274. Min Act: -0.1700
Data Index: 5880760 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.3024. Min Act: -0.1700
Data Index: 1679065 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.1774. Min Act: -0.1700
Data Index: 5135713 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.1774. Min Act: -0.1700
Data Index: 6781516 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.1149. Min Act: -0.1700
Data Index: 364797 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.1149. Min Act: -0.1700
Data Index: 5664554 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0524. Min Range: -14.0524
Max Act: 13.0524. Min Act: -0.1700
Data Index: 2998250 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.9899. Min Act: -0.1700
Data Index: 2745352 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.9274. Min Act: -0.1700
Data Index: 8319608 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.9274. Min Act: -0.1700
Data Index: 2022790 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.8649. Min Act: -0.1700
Data Index: 1263659 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.8649. Min Act: -0.1700
Data Index: 4422584 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.9899. Min Act: -0.1700
Data Index: 1255685 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.9274. Min Act: -0.1700
Data Index: 6906017 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.8649. Min Act: -0.1700
Data Index: 6372938 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.8024. Min Act: -0.1700
Data Index: 2917193 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.8024. Min Act: -0.1700
Data Index: 5196282 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0524. Min Range: -14.0524
Max Act: 12.8024. Min Act: -0.1700
Data Index: 3590551 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19