Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1123. Min Range: -8.1123
Max Act: 8.1123. Min Act: -0.1700
Data Index: 5931995 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1123. Min Range: -8.1123
Max Act: 8.1123. Min Act: -0.1700
Data Index: 1960687 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1123. Min Range: -8.1123
Max Act: 8.1123. Min Act: -0.1700
Data Index: 3914871 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1123. Min Range: -8.1123
Max Act: 8.0498. Min Act: -0.1700
Data Index: 3914869 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1123. Min Range: -8.1123
Max Act: 8.0498. Min Act: -0.1700
Data Index: 4569811 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.9873. Min Act: -0.1700
Data Index: 7376312 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.9248. Min Act: -0.1700
Data Index: 7830668 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.9248. Min Act: -0.1700
Data Index: 1960688 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.8623. Min Act: -0.1700
Data Index: 4958436 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7998. Min Act: -0.1700
Data Index: 1435741 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.8623. Min Act: -0.1700
Data Index: 8324702 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7998. Min Act: -0.1700
Data Index: 870110 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7998. Min Act: -0.1700
Data Index: 6481655 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7685. Min Act: -0.1700
Data Index: 1385870 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7685. Min Act: -0.1700
Data Index: 8569908 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7373. Min Act: -0.1700
Data Index: 4329709 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7373. Min Act: -0.1700
Data Index: 7243722 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7685. Min Act: -0.1700
Data Index: 8315267 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7060. Min Act: -0.1700
Data Index: 6400120 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1123. Min Range: -8.1123
Max Act: 7.7373. Min Act: -0.1700
Data Index: 3825666 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19