Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2058. Min Range: -4.2058
Max Act: 4.2058. Min Act: -0.1700
Data Index: 6789266 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2058. Min Range: -4.2058
Max Act: 4.1433. Min Act: -0.1700
Data Index: 7344771 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2058. Min Range: -4.2058
Max Act: 4.1120. Min Act: -0.1700
Data Index: 2471041 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2058. Min Range: -4.2058
Max Act: 4.0495. Min Act: -0.1700
Data Index: 7344770 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2058. Min Range: -4.2058
Max Act: 4.0182. Min Act: -0.1700
Data Index: 7344778 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2058. Min Range: -4.2058
Max Act: 4.0182. Min Act: -0.1700
Data Index: 3102562 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9870. Min Act: -0.1700
Data Index: 8038150 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9870. Min Act: -0.1700
Data Index: 2898002 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9870. Min Act: -0.1700
Data Index: 4425452 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9870. Min Act: -0.1700
Data Index: 2898006 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9557. Min Act: -0.1700
Data Index: 1552702 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9557. Min Act: -0.1700
Data Index: 1032878 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.8932. Min Act: -0.1700
Data Index: 6537463 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9244. Min Act: -0.1700
Data Index: 2912291 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.9244. Min Act: -0.1700
Data Index: 3689414 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.8932. Min Act: -0.1700
Data Index: 954192 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.8932. Min Act: -0.1700
Data Index: 3703654 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.8932. Min Act: -0.1700
Data Index: 4163023 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.8619. Min Act: -0.1700
Data Index: 6611151 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2058. Min Range: -4.2058
Max Act: 3.8619. Min Act: -0.1700
Data Index: 2599862 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19