Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4109 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.7193. Min Act: -0.1700
Data Index: 1221806 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.7193. Min Act: -0.1700
Data Index: 7045183 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.5943. Min Act: -0.1700
Data Index: 5100536 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.5943. Min Act: -0.1700
Data Index: 148800 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.4693. Min Act: -0.1700
Data Index: 5088598 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.5318. Min Act: -0.1700
Data Index: 7083064 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.2193. Min Act: -0.1700
Data Index: 175933 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.2193. Min Act: -0.1700
Data Index: 3400220 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.1880. Min Act: -0.1700
Data Index: 8029845 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.1568. Min Act: -0.1700
Data Index: 570244 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.1255. Min Act: -0.1700
Data Index: 4334486 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.1255. Min Act: -0.1700
Data Index: 6333590 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.1568. Min Act: -0.1700
Data Index: 1466536 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 1437210 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.1255. Min Act: -0.1700
Data Index: 1594355 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 6593569 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.0630. Min Act: -0.1700
Data Index: 4094834 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7193. Min Range: -8.7193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 5579458 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7193. Min Range: -8.7193
Max Act: 7.9693. Min Act: -0.1700
Data Index: 1261376 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7193. Min Range: -8.7193
Max Act: 7.9380. Min Act: -0.1700
Data Index: 3624064 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19