Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0501. Min Range: -4.0501
Max Act: 4.0501. Min Act: -0.1700
Data Index: 3980349 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0501. Min Range: -4.0501
Max Act: 4.0501. Min Act: -0.1700
Data Index: 3386482 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.9564. Min Act: -0.1700
Data Index: 6928601 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8938. Min Act: -0.1700
Data Index: 4087465 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8626. Min Act: -0.1700
Data Index: 953406 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8626. Min Act: -0.1700
Data Index: 7672217 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8313. Min Act: -0.1700
Data Index: 3792038 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8000. Min Act: -0.1700
Data Index: 3125920 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8000. Min Act: -0.1700
Data Index: 6279862 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.8000. Min Act: -0.1700
Data Index: 8457240 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7687. Min Act: -0.1700
Data Index: 7973902 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7687. Min Act: -0.1700
Data Index: 4797513 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7687. Min Act: -0.1700
Data Index: 5289887 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7687. Min Act: -0.1700
Data Index: 475618 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7062. Min Act: -0.1700
Data Index: 7731706 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7375. Min Act: -0.1700
Data Index: 2776283 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7375. Min Act: -0.1700
Data Index: 3249213 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7375. Min Act: -0.1700
Data Index: 8139661 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7375. Min Act: -0.1700
Data Index: 1310953 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0501. Min Range: -4.0501
Max Act: 3.7375. Min Act: -0.1700
Data Index: 7373995 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19