Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0423. Min Range: -8.0423
Max Act: 8.0423. Min Act: -0.1700
Data Index: 3331072 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.8548. Min Act: -0.1700
Data Index: 662670 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.8548. Min Act: -0.1700
Data Index: 3075967 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.8548. Min Act: -0.1700
Data Index: 5634641 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.7923. Min Act: -0.1700
Data Index: 2053090 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.6673. Min Act: -0.1700
Data Index: 735451 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.6673. Min Act: -0.1700
Data Index: 1065307 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.6360. Min Act: -0.1700
Data Index: 4821644 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.6360. Min Act: -0.1700
Data Index: 5659160 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.6048. Min Act: -0.1700
Data Index: 6595433 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5735. Min Act: -0.1700
Data Index: 7202317 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5423. Min Act: -0.1700
Data Index: 579845 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5735. Min Act: -0.1700
Data Index: 2902021 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5110. Min Act: -0.1700
Data Index: 7923394 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5423. Min Act: -0.1700
Data Index: 448710 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5110. Min Act: -0.1700
Data Index: 2097341 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5110. Min Act: -0.1700
Data Index: 1813361 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.5110. Min Act: -0.1700
Data Index: 8184695 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.4798. Min Act: -0.1700
Data Index: 1334017 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0423. Min Range: -8.0423
Max Act: 7.4485. Min Act: -0.1700
Data Index: 4815383 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19