Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.7694. Min Act: -0.1700
Data Index: 3686722 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.4569. Min Act: -0.1700
Data Index: 5434037 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.3944. Min Act: -0.1700
Data Index: 5362742 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.3319. Min Act: -0.1700
Data Index: 679917 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.3006. Min Act: -0.1700
Data Index: 7671983 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2694. Min Act: -0.1700
Data Index: 7715689 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2694. Min Act: -0.1700
Data Index: 1552757 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2381. Min Act: -0.1700
Data Index: 8208012 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2381. Min Act: -0.1700
Data Index: 8588403 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1756. Min Act: -0.1700
Data Index: 4491048 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2381. Min Act: -0.1700
Data Index: 2234099 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2069. Min Act: -0.1700
Data Index: 4379180 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1756. Min Act: -0.1700
Data Index: 6686269 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1756. Min Act: -0.1700
Data Index: 7157123 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1756. Min Act: -0.1700
Data Index: 1851721 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1756. Min Act: -0.1700
Data Index: 5434029 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.2069. Min Act: -0.1700
Data Index: 193114 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1131. Min Act: -0.1700
Data Index: 2134562 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1444. Min Act: -0.1700
Data Index: 1867579 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7694. Min Range: -7.7694
Max Act: 7.1444. Min Act: -0.1700
Data Index: 3069496 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19