Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.2655. Min Act: -0.1700
Data Index: 5753573 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1717. Min Act: -0.1700
Data Index: 3255480 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1717. Min Act: -0.1700
Data Index: 1700527 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1717. Min Act: -0.1700
Data Index: 7271412 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1405. Min Act: -0.1700
Data Index: 1098317 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1405. Min Act: -0.1700
Data Index: 163684 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1092. Min Act: -0.1700
Data Index: 7818896 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1405. Min Act: -0.1700
Data Index: 1983868 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 1268846 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1092. Min Act: -0.1700
Data Index: 3979581 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1405. Min Act: -0.1700
Data Index: 5306069 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2720073 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1092. Min Act: -0.1700
Data Index: 8810222 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.1092. Min Act: -0.1700
Data Index: 8791812 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0467. Min Act: -0.1700
Data Index: 5054551 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 4706929 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2862454 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 1887704 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 5417301 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2655. Min Range: -5.2655
Max Act: 5.0780. Min Act: -0.1700
Data Index: 673061 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19