Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.3353. Min Act: -0.1700
Data Index: 4697900 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2728. Min Act: -0.1700
Data Index: 5261676 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2416. Min Act: -0.1700
Data Index: 8251074 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2728. Min Act: -0.1700
Data Index: 6610012 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2103. Min Act: -0.1700
Data Index: 5949669 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.1791. Min Act: -0.1700
Data Index: 8132586 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2103. Min Act: -0.1700
Data Index: 6565386 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2103. Min Act: -0.1700
Data Index: 4399304 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.1791. Min Act: -0.1700
Data Index: 4546978 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.1478. Min Act: -0.1700
Data Index: 3630832 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0853. Min Act: -0.1700
Data Index: 208385 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 7299890 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 8484302 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 4909663 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0228. Min Act: -0.1700
Data Index: 843253 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0228. Min Act: -0.1700
Data Index: 676465 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 1512880 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0228. Min Act: -0.1700
Data Index: 2437592 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0228. Min Act: -0.1700
Data Index: 2970132 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0228. Min Act: -0.1700
Data Index: 8039559 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19