Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1284. Min Range: -6.1284
Max Act: 6.1284. Min Act: -0.1700
Data Index: 612956 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1284. Min Range: -6.1284
Max Act: 6.0971. Min Act: -0.1700
Data Index: 863722 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.9409. Min Act: -0.1700
Data Index: 6233889 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8784. Min Act: -0.1700
Data Index: 6893850 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.9096. Min Act: -0.1700
Data Index: 7474025 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8784. Min Act: -0.1700
Data Index: 7543808 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.9096. Min Act: -0.1700
Data Index: 8415006 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8784. Min Act: -0.1700
Data Index: 4791954 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8784. Min Act: -0.1700
Data Index: 5813990 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8784. Min Act: -0.1700
Data Index: 3019540 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8159. Min Act: -0.1700
Data Index: 166482 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8159. Min Act: -0.1700
Data Index: 4706036 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8159. Min Act: -0.1700
Data Index: 4602704 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8159. Min Act: -0.1700
Data Index: 6341452 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8159. Min Act: -0.1700
Data Index: 703784 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.7846. Min Act: -0.1700
Data Index: 8201946 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.7846. Min Act: -0.1700
Data Index: 4871904 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.7846. Min Act: -0.1700
Data Index: 2230964 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.7846. Min Act: -0.1700
Data Index: 2147394 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1284. Min Range: -6.1284
Max Act: 5.8159. Min Act: -0.1700
Data Index: 6928760 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19