Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.8892. Min Act: -0.1700
Data Index: 7862931 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7642. Min Act: -0.1700
Data Index: 2877529 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7642. Min Act: -0.1700
Data Index: 2046859 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7329. Min Act: -0.1700
Data Index: 8234544 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7642. Min Act: -0.1700
Data Index: 7977849 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7329. Min Act: -0.1700
Data Index: 5367135 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7016. Min Act: -0.1700
Data Index: 8105319 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.7016. Min Act: -0.1700
Data Index: 5245459 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6703. Min Act: -0.1700
Data Index: 4493607 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6703. Min Act: -0.1700
Data Index: 2699908 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6703. Min Act: -0.1700
Data Index: 7768031 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6703. Min Act: -0.1700
Data Index: 87880 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6703. Min Act: -0.1700
Data Index: 6854995 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6390. Min Act: -0.1700
Data Index: 6396281 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6390. Min Act: -0.1700
Data Index: 8453794 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6234. Min Act: -0.1700
Data Index: 5545470 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6234. Min Act: -0.1700
Data Index: 4276600 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.5921. Min Act: -0.1700
Data Index: 5760839 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6077. Min Act: -0.1700
Data Index: 2300229 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8892. Min Range: -3.8892
Max Act: 3.6077. Min Act: -0.1700
Data Index: 4346419 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19