Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2538 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6047. Min Range: -9.6047
Max Act: 9.6047. Min Act: -0.1700
Data Index: 894353 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6047. Min Range: -9.6047
Max Act: 9.4797. Min Act: -0.1700
Data Index: 5438860 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6047. Min Range: -9.6047
Max Act: 9.2297. Min Act: -0.1700
Data Index: 4933058 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6047. Min Range: -9.6047
Max Act: 9.2297. Min Act: -0.1700
Data Index: 2594711 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6047. Min Range: -9.6047
Max Act: 9.0422. Min Act: -0.1700
Data Index: 4661796 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.9797. Min Act: -0.1700
Data Index: 8633049 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.9797. Min Act: -0.1700
Data Index: 1818586 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.8547. Min Act: -0.1700
Data Index: 3985291 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.7922. Min Act: -0.1700
Data Index: 4776376 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.7922. Min Act: -0.1700
Data Index: 8533308 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.6672. Min Act: -0.1700
Data Index: 1429126 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.6672. Min Act: -0.1700
Data Index: 5192269 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.6672. Min Act: -0.1700
Data Index: 7413610 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.6047. Min Act: -0.1700
Data Index: 4186406 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.5422. Min Act: -0.1700
Data Index: 5863523 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.5422. Min Act: -0.1700
Data Index: 5212161 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.5422. Min Act: -0.1700
Data Index: 5155318 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.5422. Min Act: -0.1700
Data Index: 461873 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.4797. Min Act: -0.1700
Data Index: 6784482 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6047. Min Range: -9.6047
Max Act: 8.4797. Min Act: -0.1700
Data Index: 477348 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19