Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5657 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0835. Min Range: -6.0835
Max Act: 6.0835. Min Act: -0.1700
Data Index: 658662 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0835. Min Range: -6.0835
Max Act: 6.0522. Min Act: -0.1700
Data Index: 7602903 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.9897. Min Act: -0.1700
Data Index: 5299390 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0835. Min Range: -6.0835
Max Act: 6.0210. Min Act: -0.1700
Data Index: 4087920 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.9897. Min Act: -0.1700
Data Index: 2879985 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.9585. Min Act: -0.1700
Data Index: 5075998 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.9585. Min Act: -0.1700
Data Index: 2593722 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.9272. Min Act: -0.1700
Data Index: 6397153 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.9272. Min Act: -0.1700
Data Index: 8668429 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.8647. Min Act: -0.1700
Data Index: 5799064 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.8647. Min Act: -0.1700
Data Index: 5071281 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.8335. Min Act: -0.1700
Data Index: 6618099 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.8022. Min Act: -0.1700
Data Index: 2443581 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.8022. Min Act: -0.1700
Data Index: 2976627 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.7710. Min Act: -0.1700
Data Index: 8815938 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.8022. Min Act: -0.1700
Data Index: 3796497 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.7710. Min Act: -0.1700
Data Index: 8646562 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.7397. Min Act: -0.1700
Data Index: 757540 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.7085. Min Act: -0.1700
Data Index: 2513901 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0835. Min Range: -6.0835
Max Act: 5.7085. Min Act: -0.1700
Data Index: 4625405 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19