Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3616 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1376. Min Range: -5.1376
Max Act: 5.1063. Min Act: -0.1700
Data Index: 7686058 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1376. Min Range: -5.1376
Max Act: 5.1376. Min Act: -0.1700
Data Index: 3060330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.9813. Min Act: -0.1700
Data Index: 457370 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.9188. Min Act: -0.1700
Data Index: 6009950 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8876. Min Act: -0.1699
Data Index: 3342015 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8876. Min Act: -0.1700
Data Index: 1712579 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8876. Min Act: -0.1700
Data Index: 4127521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8876. Min Act: -0.1700
Data Index: 6458292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8876. Min Act: -0.1700
Data Index: 1306780 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4251866 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8876. Min Act: -0.1700
Data Index: 4492545 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4555284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8563. Min Act: -0.1700
Data Index: 6512433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8251. Min Act: -0.1700
Data Index: 6195372 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8251. Min Act: -0.1700
Data Index: 6202892 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8251. Min Act: -0.1700
Data Index: 608130 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8251. Min Act: -0.1700
Data Index: 5015651 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8251. Min Act: -0.1700
Data Index: 5428693 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.8251. Min Act: -0.1700
Data Index: 7191814 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1376. Min Range: -5.1376
Max Act: 4.7938. Min Act: -0.1700
Data Index: 5806490 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19