Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.7024. Min Act: -0.1700
Data Index: 4326266 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.6711. Min Act: -0.1700
Data Index: 5687568 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.5774. Min Act: -0.1700
Data Index: 4587828 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.3586. Min Act: -0.1700
Data Index: 8372323 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.3274. Min Act: -0.1700
Data Index: 5697958 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2961. Min Act: -0.1700
Data Index: 1606829 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2961. Min Act: -0.1700
Data Index: 219678 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.3274. Min Act: -0.1700
Data Index: 6800453 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2336. Min Act: -0.1700
Data Index: 4602666 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2649. Min Act: -0.1700
Data Index: 73900 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2336. Min Act: -0.1700
Data Index: 134079 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2024. Min Act: -0.1700
Data Index: 7855766 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.2024. Min Act: -0.1700
Data Index: 1268819 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.1711. Min Act: -0.1700
Data Index: 4773544 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.1711. Min Act: -0.1700
Data Index: 2377736 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.1399. Min Act: -0.1700
Data Index: 3231596 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.1399. Min Act: -0.1700
Data Index: 3390011 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.1399. Min Act: -0.1700
Data Index: 8284593 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.0774. Min Act: -0.1700
Data Index: 93659 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7024. Min Range: -5.7024
Max Act: 5.1086. Min Act: -0.1700
Data Index: 6669046 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19