Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2477. Min Range: -6.2477
Max Act: 6.2477. Min Act: -0.1700
Data Index: 6511438 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2477. Min Range: -6.2477
Max Act: 6.2164. Min Act: -0.1700
Data Index: 1307325 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.8102. Min Act: -0.1700
Data Index: 1073130 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 1329277 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 5462008 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 6101937 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 4698563 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 3898107 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 1869303 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 676005 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 3796903 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7164. Min Act: -0.1700
Data Index: 4403548 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 459308 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 3194171 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 4436104 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 893988 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7789. Min Act: -0.1700
Data Index: 4698558 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 1932054 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7477. Min Act: -0.1700
Data Index: 2010928 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2477. Min Range: -6.2477
Max Act: 5.7164. Min Act: -0.1700
Data Index: 4698565 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19