Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1312. Min Range: -9.1312
Max Act: 9.1312. Min Act: -0.1700
Data Index: 1315236 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1312. Min Range: -9.1312
Max Act: 9.0687. Min Act: -0.1700
Data Index: 8154243 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.9437. Min Act: -0.1700
Data Index: 3342114 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.7562. Min Act: -0.1700
Data Index: 944395 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.6937. Min Act: -0.1700
Data Index: 3459449 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.6312. Min Act: -0.1700
Data Index: 7922140 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.6312. Min Act: -0.1700
Data Index: 7387672 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.6312. Min Act: -0.1700
Data Index: 7595987 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.6312. Min Act: -0.1700
Data Index: 3030650 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5687. Min Act: -0.1700
Data Index: 1407415 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5687. Min Act: -0.1700
Data Index: 2976564 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5687. Min Act: -0.1700
Data Index: 1074926 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5687. Min Act: -0.1700
Data Index: 7558601 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5687. Min Act: -0.1700
Data Index: 1180907 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5062. Min Act: -0.1700
Data Index: 6314954 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5062. Min Act: -0.1700
Data Index: 7437679 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5062. Min Act: -0.1700
Data Index: 3125807 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.5062. Min Act: -0.1700
Data Index: 6167566 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.4437. Min Act: -0.1700
Data Index: 7294430 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1312. Min Range: -9.1312
Max Act: 8.4437. Min Act: -0.1700
Data Index: 6894812 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19