Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4987 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.5010. Min Act: -0.1700
Data Index: 3060035 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2510. Min Act: -0.1700
Data Index: 8809135 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1885. Min Act: -0.1700
Data Index: 566796 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1885. Min Act: -0.1700
Data Index: 5521216 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1260. Min Act: -0.1700
Data Index: 7290674 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1260. Min Act: -0.1700
Data Index: 7785616 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1260. Min Act: -0.1700
Data Index: 7785615 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0635. Min Act: -0.1700
Data Index: 4897822 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0323. Min Act: -0.1700
Data Index: 1134333 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0635. Min Act: -0.1700
Data Index: 1911805 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0635. Min Act: -0.1700
Data Index: 3976622 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0010. Min Act: -0.1700
Data Index: 6715991 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0010. Min Act: -0.1700
Data Index: 8271672 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0010. Min Act: -0.1700
Data Index: 673591 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.0010. Min Act: -0.1700
Data Index: 2482843 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5010. Min Range: -5.5010
Max Act: 4.9698. Min Act: -0.1700
Data Index: 7180629 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5010. Min Range: -5.5010
Max Act: 4.9385. Min Act: -0.1700
Data Index: 6557693 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5010. Min Range: -5.5010
Max Act: 4.9698. Min Act: -0.1700
Data Index: 6410804 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5010. Min Range: -5.5010
Max Act: 4.9698. Min Act: -0.1700
Data Index: 8714012 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5010. Min Range: -5.5010
Max Act: 4.9698. Min Act: -0.1700
Data Index: 7046896 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19