Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3822. Min Range: -6.3822
Max Act: 6.3822. Min Act: -0.1700
Data Index: 6183237 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3822. Min Range: -6.3822
Max Act: 6.2259. Min Act: -0.1700
Data Index: 6338687 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3822. Min Range: -6.3822
Max Act: 6.1634. Min Act: -0.1700
Data Index: 5550116 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.9447. Min Act: -0.1700
Data Index: 8071932 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.9447. Min Act: -0.1700
Data Index: 7300653 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.9447. Min Act: -0.1700
Data Index: 1867151 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.8822. Min Act: -0.1700
Data Index: 4291275 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.8509. Min Act: -0.1700
Data Index: 1504257 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.8197. Min Act: -0.1700
Data Index: 3258588 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.8197. Min Act: -0.1700
Data Index: 2281815 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.8197. Min Act: -0.1700
Data Index: 7555847 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7884. Min Act: -0.1700
Data Index: 7047471 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7572. Min Act: -0.1700
Data Index: 3640687 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7572. Min Act: -0.1700
Data Index: 8132119 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7572. Min Act: -0.1700
Data Index: 6169380 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7259. Min Act: -0.1700
Data Index: 2387734 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7259. Min Act: -0.1700
Data Index: 2215164 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7259. Min Act: -0.1700
Data Index: 32640 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.7259. Min Act: -0.1700
Data Index: 2531103 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3822. Min Range: -6.3822
Max Act: 5.6947. Min Act: -0.1700
Data Index: 6045859 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19