Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5942 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.7509. Min Act: -0.1700
Data Index: 2077429 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.3134. Min Act: -0.1700
Data Index: 7220224 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.2509. Min Act: -0.1700
Data Index: 7146562 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.1259. Min Act: -0.1700
Data Index: 693889 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.0634. Min Act: -0.1700
Data Index: 8075863 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.0009. Min Act: -0.1700
Data Index: 5703077 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7509. Min Range: -8.7509
Max Act: 8.0634. Min Act: -0.1700
Data Index: 5096672 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.9384. Min Act: -0.1700
Data Index: 2147167 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.9384. Min Act: -0.1700
Data Index: 7444311 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8759. Min Act: -0.1700
Data Index: 6453169 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8759. Min Act: -0.1700
Data Index: 3031447 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8759. Min Act: -0.1700
Data Index: 6395805 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8134. Min Act: -0.1700
Data Index: 5936849 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8134. Min Act: -0.1700
Data Index: 6053839 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8134. Min Act: -0.1700
Data Index: 4978626 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8134. Min Act: -0.1700
Data Index: 4967923 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.8134. Min Act: -0.1700
Data Index: 2758013 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.7509. Min Act: -0.1700
Data Index: 4112498 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.6884. Min Act: -0.1700
Data Index: 689963 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7509. Min Range: -8.7509
Max Act: 7.6884. Min Act: -0.1700
Data Index: 5629236 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19