Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2852 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3417. Min Range: -2.3417
Max Act: 2.3417. Min Act: -0.1692
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3417. Min Range: -2.3417
Max Act: 1.8389. Min Act: -0.1700
Data Index: 8752172 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.9733. Min Act: -0.1700
Data Index: 8752176 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7776. Min Act: -0.1700
Data Index: 8449070 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7693. Min Act: -0.1700
Data Index: 2902808 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7361. Min Act: -0.1697
Data Index: 448769 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7279. Min Act: -0.1700
Data Index: 4263897 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7279. Min Act: -0.1700
Data Index: 7084529 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7197. Min Act: -0.1700
Data Index: 4292546 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7115. Min Act: -0.1700
Data Index: 5657166 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7115. Min Act: -0.1700
Data Index: 6367152 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7115. Min Act: -0.1700
Data Index: 5657167 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.7033. Min Act: -0.1700
Data Index: 6057535 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6951. Min Act: -0.1692
Data Index: 7210241 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6870. Min Act: -0.1700
Data Index: 481557 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6870. Min Act: -0.1700
Data Index: 2743907 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6789. Min Act: -0.1700
Data Index: 6434509 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6789. Min Act: -0.1700
Data Index: 1817879 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6789. Min Act: -0.1700
Data Index: 4263903 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3417. Min Range: -2.3417
Max Act: 0.6789. Min Act: -0.1699
Data Index: 4303363 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19