Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.4226. Min Act: -0.1700
Data Index: 8361199 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1414. Min Act: -0.1700
Data Index: 3112257 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1101. Min Act: -0.1700
Data Index: 1887896 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.1414. Min Act: -0.1700
Data Index: 3265193 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0789. Min Act: -0.1700
Data Index: 1560734 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0789. Min Act: -0.1700
Data Index: 3153906 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0789. Min Act: -0.1700
Data Index: 4077720 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0164. Min Act: -0.1700
Data Index: 6195275 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0476. Min Act: -0.1700
Data Index: 2492793 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0164. Min Act: -0.1700
Data Index: 5803911 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4226. Min Range: -5.4226
Max Act: 5.0164. Min Act: -0.1700
Data Index: 8121114 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9851. Min Act: -0.1700
Data Index: 3140118 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2709868 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9851. Min Act: -0.1700
Data Index: 1923570 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9539. Min Act: -0.1700
Data Index: 1915863 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9851. Min Act: -0.1700
Data Index: 648920 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9226. Min Act: -0.1700
Data Index: 981850 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9539. Min Act: -0.1700
Data Index: 2292453 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9226. Min Act: -0.1700
Data Index: 8175837 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4226. Min Range: -5.4226
Max Act: 4.9539. Min Act: -0.1700
Data Index: 8738805 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19