Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 523 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.8928. Min Act: -0.1700
Data Index: 8098354 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.8616. Min Act: -0.1700
Data Index: 5953427 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.8303. Min Act: -0.1700
Data Index: 6717573 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.8303. Min Act: -0.1700
Data Index: 7865660 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7991. Min Act: -0.1700
Data Index: 2130244 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.8616. Min Act: -0.1700
Data Index: 4785574 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7678. Min Act: -0.1700
Data Index: 4095960 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7991. Min Act: -0.1700
Data Index: 5386911 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7991. Min Act: -0.1700
Data Index: 4917756 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7678. Min Act: -0.1700
Data Index: 2366640 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7366. Min Act: -0.1700
Data Index: 5765820 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7053. Min Act: -0.1700
Data Index: 8053254 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.7053. Min Act: -0.1700
Data Index: 4373243 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 7827444 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 303066 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 2541081 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 3814506 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 7257301 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 6685923 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8928. Min Range: -5.8928
Max Act: 5.6741. Min Act: -0.1700
Data Index: 5258934 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19