Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1835 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.8892. Min Act: -0.1700
Data Index: 5096905 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.7955. Min Act: -0.1700
Data Index: 478185 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.7017. Min Act: -0.1700
Data Index: 4079980 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.6080. Min Act: -0.1700
Data Index: 6782465 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.4205. Min Act: -0.1700
Data Index: 4410335 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.3580. Min Act: -0.1700
Data Index: 5702414 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.3892. Min Act: -0.1700
Data Index: 932564 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.3580. Min Act: -0.1700
Data Index: 7355679 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.3267. Min Act: -0.1700
Data Index: 4362709 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2955. Min Act: -0.1700
Data Index: 3774222 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2955. Min Act: -0.1700
Data Index: 2112273 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2642. Min Act: -0.1700
Data Index: 5055890 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2642. Min Act: -0.1700
Data Index: 4313199 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2642. Min Act: -0.1700
Data Index: 2687679 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 3881416 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2330. Min Act: -0.1700
Data Index: 7165254 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2330. Min Act: -0.1700
Data Index: 6138954 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 1840410 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 1769285 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8892. Min Range: -7.8892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 2031251 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19