Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1828 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.8471. Min Act: -0.1700
Data Index: 5213541 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.4096. Min Act: -0.1700
Data Index: 3857510 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.2846. Min Act: -0.1700
Data Index: 152518 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.2846. Min Act: -0.1700
Data Index: 7020642 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.1596. Min Act: -0.1700
Data Index: 8448148 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.0346. Min Act: -0.1700
Data Index: 7369964 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.0346. Min Act: -0.1700
Data Index: 158759 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8471. Min Range: -10.8471
Max Act: 10.0346. Min Act: -0.1700
Data Index: 650022 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.9721. Min Act: -0.1700
Data Index: 8562847 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.9721. Min Act: -0.1700
Data Index: 1184469 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.9096. Min Act: -0.1700
Data Index: 3222044 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.9096. Min Act: -0.1700
Data Index: 397741 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.8471. Min Act: -0.1700
Data Index: 432035 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.8471. Min Act: -0.1700
Data Index: 4856292 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.7846. Min Act: -0.1700
Data Index: 6358206 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.7846. Min Act: -0.1700
Data Index: 2097755 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.7846. Min Act: -0.1700
Data Index: 8258777 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.7221. Min Act: -0.1700
Data Index: 5068786 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.6596. Min Act: -0.1700
Data Index: 340257 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8471. Min Range: -10.8471
Max Act: 9.6596. Min Act: -0.1700
Data Index: 4987397 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19