Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8168. Min Act: -0.1700
Data Index: 4486581 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8168. Min Act: -0.1700
Data Index: 760713 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8168. Min Act: -0.1700
Data Index: 3679376 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8009. Min Act: -0.1700
Data Index: 1274286 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.8009. Min Act: -0.1700
Data Index: 4472955 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7850. Min Act: -0.1700
Data Index: 1591145 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7690. Min Act: -0.1700
Data Index: 4298264 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7690. Min Act: -0.1700
Data Index: 666959 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 6117678 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7690. Min Act: -0.1700
Data Index: 7055757 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 4326555 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7690. Min Act: -0.1700
Data Index: 737386 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 7502568 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7531. Min Act: -0.1700
Data Index: 8767354 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 7062910 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7211. Min Act: -0.1700
Data Index: 490758 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 1192645 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 839490 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 2951286 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8168. Min Range: -2.8168
Max Act: 2.7371. Min Act: -0.1700
Data Index: 1416262 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19