Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 361 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0675. Min Range: -5.0675
Max Act: 5.0675. Min Act: -0.1700
Data Index: 1456821 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.9112. Min Act: -0.1700
Data Index: 6146658 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.8800. Min Act: -0.1700
Data Index: 1658227 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.8175. Min Act: -0.1700
Data Index: 6199321 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 7249238 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.7237. Min Act: -0.1700
Data Index: 6037952 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.7237. Min Act: -0.1700
Data Index: 194014 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 1841797 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 1079154 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6925. Min Act: -0.1700
Data Index: 2401731 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6612. Min Act: -0.1700
Data Index: 5589371 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.6612. Min Act: -0.1700
Data Index: 6947711 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5987. Min Act: -0.1700
Data Index: 32516 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5987. Min Act: -0.1700
Data Index: 3649362 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5987. Min Act: -0.1700
Data Index: 2026552 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 2535316 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 4823878 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 6765745 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5987. Min Act: -0.1700
Data Index: 135530 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0675. Min Range: -5.0675
Max Act: 4.5675. Min Act: -0.1700
Data Index: 190523 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19