Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1855 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2505. Min Range: -8.2505
Max Act: 8.2505. Min Act: -0.1700
Data Index: 1473452 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2505. Min Range: -8.2505
Max Act: 8.1255. Min Act: -0.1700
Data Index: 8559349 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.8755. Min Act: -0.1700
Data Index: 4873671 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.8130. Min Act: -0.1700
Data Index: 3834640 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.7505. Min Act: -0.1700
Data Index: 3215747 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.6255. Min Act: -0.1700
Data Index: 2550232 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.6880. Min Act: -0.1700
Data Index: 8661346 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.6255. Min Act: -0.1700
Data Index: 8022274 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.6255. Min Act: -0.1700
Data Index: 4144710 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.6255. Min Act: -0.1700
Data Index: 754981 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.5630. Min Act: -0.1700
Data Index: 1964817 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.5630. Min Act: -0.1700
Data Index: 5578876 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.5630. Min Act: -0.1700
Data Index: 3772203 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.5630. Min Act: -0.1700
Data Index: 8720471 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.5005. Min Act: -0.1700
Data Index: 7012731 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.5005. Min Act: -0.1700
Data Index: 3285542 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.4692. Min Act: -0.1700
Data Index: 4964119 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.4692. Min Act: -0.1700
Data Index: 8547694 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.4692. Min Act: -0.1700
Data Index: 8184577 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2505. Min Range: -8.2505
Max Act: 7.4692. Min Act: -0.1700
Data Index: 6325352 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19