Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1779 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.5511. Min Act: -0.1700
Data Index: 8320024 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.1761. Min Act: -0.1700
Data Index: 3632665 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5511. Min Range: -6.5511
Max Act: 6.0823. Min Act: -0.1700
Data Index: 3746820 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.9261. Min Act: -0.1700
Data Index: 693344 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.8323. Min Act: -0.1700
Data Index: 2885874 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.8011. Min Act: -0.1700
Data Index: 2144500 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.7386. Min Act: -0.1700
Data Index: 5582110 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2078697 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.7073. Min Act: -0.1700
Data Index: 3845658 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.7073. Min Act: -0.1700
Data Index: 3280255 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.6761. Min Act: -0.1700
Data Index: 6530647 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.6136. Min Act: -0.1700
Data Index: 8021982 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 4758469 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.5823. Min Act: -0.1700
Data Index: 794514 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.5198. Min Act: -0.1700
Data Index: 6010054 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.5198. Min Act: -0.1700
Data Index: 2354405 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.4886. Min Act: -0.1700
Data Index: 4861876 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.4573. Min Act: -0.1700
Data Index: 8419159 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.4573. Min Act: -0.1700
Data Index: 504808 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5511. Min Range: -6.5511
Max Act: 5.4573. Min Act: -0.1700
Data Index: 7472862 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19