Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5249 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.6880. Min Act: -0.1700
Data Index: 53631 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.5630. Min Act: -0.1700
Data Index: 8202853 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.5317. Min Act: -0.1700
Data Index: 6307913 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.5317. Min Act: -0.1700
Data Index: 8428065 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.4380. Min Act: -0.1700
Data Index: 5837268 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.4380. Min Act: -0.1700
Data Index: 1577105 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.3130. Min Act: -0.1700
Data Index: 4799969 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.2817. Min Act: -0.1700
Data Index: 8015274 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.2505. Min Act: -0.1700
Data Index: 4571723 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.1880. Min Act: -0.1700
Data Index: 605131 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.2192. Min Act: -0.1700
Data Index: 7325795 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.2192. Min Act: -0.1700
Data Index: 7130130 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.1255. Min Act: -0.1700
Data Index: 1493696 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.1255. Min Act: -0.1700
Data Index: 4666978 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.0630. Min Act: -0.1700
Data Index: 4397903 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.0630. Min Act: -0.1700
Data Index: 7706230 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6880. Min Range: -7.6880
Max Act: 7.0317. Min Act: -0.1700
Data Index: 3258523 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6880. Min Range: -7.6880
Max Act: 6.9692. Min Act: -0.1700
Data Index: 6286377 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6880. Min Range: -7.6880
Max Act: 6.9692. Min Act: -0.1700
Data Index: 3368467 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6880. Min Range: -7.6880
Max Act: 6.9692. Min Act: -0.1700
Data Index: 3206604 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19