Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0766. Min Range: -4.0766
Max Act: 4.0766. Min Act: -0.1700
Data Index: 6375131 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9829. Min Act: -0.1700
Data Index: 4466780 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9203. Min Act: -0.1700
Data Index: 7758263 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.9203. Min Act: -0.1700
Data Index: 469697 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8265. Min Act: -0.1700
Data Index: 4436847 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8265. Min Act: -0.1700
Data Index: 1136235 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.8265. Min Act: -0.1700
Data Index: 1388660 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7952. Min Act: -0.1700
Data Index: 1961484 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7640. Min Act: -0.1700
Data Index: 7828837 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7327. Min Act: -0.1700
Data Index: 1560656 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7327. Min Act: -0.1700
Data Index: 6052253 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7327. Min Act: -0.1700
Data Index: 3550187 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7014. Min Act: -0.1700
Data Index: 4548153 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7014. Min Act: -0.1700
Data Index: 5180881 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7014. Min Act: -0.1700
Data Index: 8196687 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.6701. Min Act: -0.1700
Data Index: 2476398 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7014. Min Act: -0.1700
Data Index: 5417758 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.7014. Min Act: -0.1700
Data Index: 8125062 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.6701. Min Act: -0.1700
Data Index: 5348206 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0766. Min Range: -4.0766
Max Act: 3.6701. Min Act: -0.1700
Data Index: 2935185 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19