Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4216 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.6991. Min Act: -0.1700
Data Index: 4783163 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.5116. Min Act: -0.1700
Data Index: 1896103 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.5116. Min Act: -0.1700
Data Index: 3860289 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.4491. Min Act: -0.1700
Data Index: 58237 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.4178. Min Act: -0.1700
Data Index: 5807928 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.3866. Min Act: -0.1700
Data Index: 8682861 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.3553. Min Act: -0.1700
Data Index: 7391244 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.2928. Min Act: -0.1700
Data Index: 156698 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.2616. Min Act: -0.1700
Data Index: 6499752 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.1366. Min Act: -0.1700
Data Index: 2458743 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.1991. Min Act: -0.1700
Data Index: 5055686 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.1678. Min Act: -0.1700
Data Index: 753456 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.1366. Min Act: -0.1700
Data Index: 1617283 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.1053. Min Act: -0.1700
Data Index: 6562175 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.0428. Min Act: -0.1700
Data Index: 578337 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.0428. Min Act: -0.1700
Data Index: 4799017 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.0116. Min Act: -0.1700
Data Index: 1173360 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.0116. Min Act: -0.1700
Data Index: 7073031 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6991. Min Range: -6.6991
Max Act: 6.0116. Min Act: -0.1700
Data Index: 3797454 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6991. Min Range: -6.6991
Max Act: 5.9803. Min Act: -0.1700
Data Index: 5289383 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19