Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.3420. Min Act: -0.1700
Data Index: 6967515 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.2170. Min Act: -0.1700
Data Index: 3587313 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.1545. Min Act: -0.1700
Data Index: 4443557 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.1857. Min Act: -0.1700
Data Index: 2815450 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.1857. Min Act: -0.1700
Data Index: 8501812 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0920. Min Act: -0.1700
Data Index: 6426802 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0920. Min Act: -0.1700
Data Index: 6644258 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0607. Min Act: -0.1700
Data Index: 2341732 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0607. Min Act: -0.1700
Data Index: 2131855 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0607. Min Act: -0.1700
Data Index: 6072042 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0295. Min Act: -0.1700
Data Index: 6305339 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0295. Min Act: -0.1700
Data Index: 5349307 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0295. Min Act: -0.1700
Data Index: 8675642 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3420. Min Range: -5.3420
Max Act: 4.9982. Min Act: -0.1700
Data Index: 6656216 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0295. Min Act: -0.1700
Data Index: 6690140 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3420. Min Range: -5.3420
Max Act: 5.0295. Min Act: -0.1700
Data Index: 8429994 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3420. Min Range: -5.3420
Max Act: 4.9982. Min Act: -0.1700
Data Index: 3576117 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3420. Min Range: -5.3420
Max Act: 4.9670. Min Act: -0.1700
Data Index: 1111099 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3420. Min Range: -5.3420
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4013204 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3420. Min Range: -5.3420
Max Act: 4.9982. Min Act: -0.1700
Data Index: 6985202 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19