Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1281 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.9340. Min Act: -0.1700
Data Index: 8554172 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.4653. Min Act: -0.1700
Data Index: 4644895 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.4340. Min Act: -0.1700
Data Index: 4554127 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.4340. Min Act: -0.1700
Data Index: 2765721 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.3403. Min Act: -0.1700
Data Index: 2454924 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.3403. Min Act: -0.1700
Data Index: 7901472 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.3090. Min Act: -0.1700
Data Index: 7812416 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.2465. Min Act: -0.1700
Data Index: 3819308 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.1528. Min Act: -0.1700
Data Index: 8711701 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.1840. Min Act: -0.1700
Data Index: 7222732 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.1840. Min Act: -0.1700
Data Index: 162828 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.1528. Min Act: -0.1700
Data Index: 4804786 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.1528. Min Act: -0.1700
Data Index: 7757837 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.0903. Min Act: -0.1700
Data Index: 5947233 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.0903. Min Act: -0.1700
Data Index: 199446 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.0903. Min Act: -0.1700
Data Index: 4077639 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.0590. Min Act: -0.1700
Data Index: 8202817 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.1215. Min Act: -0.1700
Data Index: 3563084 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9340. Min Range: -7.9340
Max Act: 7.0903. Min Act: -0.1700
Data Index: 7604342 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9340. Min Range: -7.9340
Max Act: 6.9965. Min Act: -0.1700
Data Index: 5457447 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19