Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2873 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.9724. Min Act: -0.1700
Data Index: 2471015 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.9099. Min Act: -0.1700
Data Index: 5258526 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.8474. Min Act: -0.1700
Data Index: 4729789 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.8474. Min Act: -0.1700
Data Index: 1873931 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.8162. Min Act: -0.1700
Data Index: 1897978 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7537. Min Act: -0.1700
Data Index: 4734983 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7849. Min Act: -0.1700
Data Index: 6635668 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7849. Min Act: -0.1700
Data Index: 4260083 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7537. Min Act: -0.1700
Data Index: 2824204 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7537. Min Act: -0.1700
Data Index: 2860027 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7537. Min Act: -0.1700
Data Index: 2912711 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7537. Min Act: -0.1700
Data Index: 7589584 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 2467749 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 8538739 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 8538734 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 7407035 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 2170857 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 5236318 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 361833 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9724. Min Range: -5.9724
Max Act: 5.7224. Min Act: -0.1700
Data Index: 1825784 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19