Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4419. Min Range: -6.4419
Max Act: 6.4419. Min Act: -0.1700
Data Index: 1916566 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4419. Min Range: -6.4419
Max Act: 6.2544. Min Act: -0.1700
Data Index: 3636418 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.9419. Min Act: -0.1700
Data Index: 4520155 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.8794. Min Act: -0.1700
Data Index: 4239952 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.7544. Min Act: -0.1700
Data Index: 8489480 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.6919. Min Act: -0.1700
Data Index: 4321722 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.6919. Min Act: -0.1700
Data Index: 2524831 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.6919. Min Act: -0.1700
Data Index: 2352062 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.6607. Min Act: -0.1700
Data Index: 4914874 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.6294. Min Act: -0.1700
Data Index: 8355927 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5982. Min Act: -0.1700
Data Index: 8660019 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5982. Min Act: -0.1700
Data Index: 8216130 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5982. Min Act: -0.1700
Data Index: 2820061 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5982. Min Act: -0.1700
Data Index: 7744342 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5982. Min Act: -0.1700
Data Index: 1449232 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5669. Min Act: -0.1700
Data Index: 3609375 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5669. Min Act: -0.1700
Data Index: 8138698 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5669. Min Act: -0.1700
Data Index: 7581974 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5357. Min Act: -0.1700
Data Index: 7029643 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4419. Min Range: -6.4419
Max Act: 5.5669. Min Act: -0.1700
Data Index: 4297732 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19