Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.8579. Min Act: -0.1700
Data Index: 1146995 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.8579. Min Act: -0.1700
Data Index: 3333880 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.5766. Min Act: -0.1700
Data Index: 5144908 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.5141. Min Act: -0.1700
Data Index: 4244914 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.4516. Min Act: -0.1700
Data Index: 837571 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.4516. Min Act: -0.1700
Data Index: 8180009 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3891. Min Act: -0.1700
Data Index: 8784513 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.4204. Min Act: -0.1700
Data Index: 5700307 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.4204. Min Act: -0.1700
Data Index: 2690877 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3891. Min Act: -0.1700
Data Index: 6312664 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3891. Min Act: -0.1700
Data Index: 53068 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3891. Min Act: -0.1700
Data Index: 2690875 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3891. Min Act: -0.1700
Data Index: 103783 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3579. Min Act: -0.1700
Data Index: 7781773 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3579. Min Act: -0.1700
Data Index: 2778811 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3891. Min Act: -0.1700
Data Index: 5351121 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3579. Min Act: -0.1700
Data Index: 5070698 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3266. Min Act: -0.1700
Data Index: 5073825 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3266. Min Act: -0.1700
Data Index: 1187406 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8579. Min Range: -7.8579
Max Act: 7.3266. Min Act: -0.1700
Data Index: 6882763 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19