Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1811. Min Range: -16.1811
Max Act: 16.1811. Min Act: -0.1700
Data Index: 2098120 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.8061. Min Act: -0.1700
Data Index: 414608 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.8061. Min Act: -0.1700
Data Index: 8609199 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.4311. Min Act: -0.1700
Data Index: 1827004 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.3061. Min Act: -0.1700
Data Index: 1128606 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.3061. Min Act: -0.1700
Data Index: 7863134 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.2436. Min Act: -0.1700
Data Index: 4585061 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.1811. Min Act: -0.1700
Data Index: 6761518 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.1186. Min Act: -0.1700
Data Index: 7019250 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.1186. Min Act: -0.1700
Data Index: 8749692 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 2852302 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.1186. Min Act: -0.1700
Data Index: 6760600 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 2460645 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1811. Min Range: -16.1811
Max Act: 14.9936. Min Act: -0.1700
Data Index: 5236940 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1811. Min Range: -16.1811
Max Act: 14.9936. Min Act: -0.1700
Data Index: 7747950 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 2640288 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 2466950 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 1517899 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 3457031 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1811. Min Range: -16.1811
Max Act: 15.0561. Min Act: -0.1700
Data Index: 6276900 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19