Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0353. Min Range: -9.0353
Max Act: 9.0353. Min Act: -0.1700
Data Index: 4032825 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.9103. Min Act: -0.1700
Data Index: 7442971 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.9103. Min Act: -0.1700
Data Index: 729655 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.9728. Min Act: -0.1700
Data Index: 8126348 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.9103. Min Act: -0.1700
Data Index: 4122409 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.8478. Min Act: -0.1700
Data Index: 2731910 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.7853. Min Act: -0.1700
Data Index: 60929 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.7228. Min Act: -0.1700
Data Index: 7521710 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.7853. Min Act: -0.1700
Data Index: 7259574 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.7228. Min Act: -0.1700
Data Index: 8037127 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.6603. Min Act: -0.1700
Data Index: 6733562 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.6603. Min Act: -0.1700
Data Index: 4480106 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.6603. Min Act: -0.1700
Data Index: 8231417 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.6603. Min Act: -0.1700
Data Index: 1758749 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.5978. Min Act: -0.1700
Data Index: 2118051 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.6603. Min Act: -0.1700
Data Index: 6884937 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.5353. Min Act: -0.1700
Data Index: 7845137 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.5353. Min Act: -0.1700
Data Index: 7995502 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.5353. Min Act: -0.1700
Data Index: 6488128 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0353. Min Range: -9.0353
Max Act: 8.5353. Min Act: -0.1700
Data Index: 5740593 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19