Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2573 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.4601. Min Act: -0.1700
Data Index: 2428521 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.4601. Min Act: -0.1700
Data Index: 4860397 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.5226. Min Act: -0.1700
Data Index: 4516050 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.4601. Min Act: -0.1700
Data Index: 3047692 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.3351. Min Act: -0.1700
Data Index: 4860422 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.2726. Min Act: -0.1700
Data Index: 4860396 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.2101. Min Act: -0.1700
Data Index: 4088231 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.1476. Min Act: -0.1700
Data Index: 4860395 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 8690570 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 4860404 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 7411411 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 1018937 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 6541043 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 2141522 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5226. Min Range: -8.5226
Max Act: 8.0851. Min Act: -0.1700
Data Index: 2827888 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5226. Min Range: -8.5226
Max Act: 7.9601. Min Act: -0.1700
Data Index: 4860393 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5226. Min Range: -8.5226
Max Act: 7.9601. Min Act: -0.1700
Data Index: 2884334 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5226. Min Range: -8.5226
Max Act: 7.9601. Min Act: -0.1700
Data Index: 39334 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5226. Min Range: -8.5226
Max Act: 7.9289. Min Act: -0.1700
Data Index: 4860394 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5226. Min Range: -8.5226
Max Act: 7.9289. Min Act: -0.1700
Data Index: 1002675 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19