Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4023 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.3196. Min Act: -0.1700
Data Index: 6605557 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.2571. Min Act: -0.1700
Data Index: 1215255 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0695. Min Act: -0.1700
Data Index: 7651456 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0383. Min Act: -0.1700
Data Index: 5833864 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0383. Min Act: -0.1700
Data Index: 1412086 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0383. Min Act: -0.1700
Data Index: 7447901 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0383. Min Act: -0.1700
Data Index: 4158135 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0070. Min Act: -0.1700
Data Index: 1331513 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0070. Min Act: -0.1700
Data Index: 8190103 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9757. Min Act: -0.1700
Data Index: 911231 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9757. Min Act: -0.1700
Data Index: 7604720 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9757. Min Act: -0.1700
Data Index: 7256028 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9757. Min Act: -0.1700
Data Index: 6296223 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3196. Min Range: -4.3196
Max Act: 4.0070. Min Act: -0.1700
Data Index: 6112473 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9757. Min Act: -0.1700
Data Index: 6112454 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9445. Min Act: -0.1700
Data Index: 1339984 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9445. Min Act: -0.1700
Data Index: 6255951 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9757. Min Act: -0.1700
Data Index: 6112474 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9445. Min Act: -0.1700
Data Index: 7870262 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3196. Min Range: -4.3196
Max Act: 3.9132. Min Act: -0.1700
Data Index: 3599615 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19