Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.8093. Min Act: -0.1700
Data Index: 2503213 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.7155. Min Act: -0.1700
Data Index: 8765729 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.4343. Min Act: -0.1700
Data Index: 7191425 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.4030. Min Act: -0.1700
Data Index: 517617 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.3718. Min Act: -0.1700
Data Index: 5562412 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.3718. Min Act: -0.1700
Data Index: 8673751 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.3093. Min Act: -0.1700
Data Index: 3645904 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.3093. Min Act: -0.1700
Data Index: 4740085 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.2155. Min Act: -0.1700
Data Index: 2113790 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1843. Min Act: -0.1700
Data Index: 7509728 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 1647041 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 778990 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1843. Min Act: -0.1700
Data Index: 5298618 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 6927003 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 1679234 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1530. Min Act: -0.1700
Data Index: 8189868 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1218. Min Act: -0.1700
Data Index: 3613897 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.1218. Min Act: -0.1700
Data Index: 1315441 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.0593. Min Act: -0.1700
Data Index: 7074206 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8093. Min Range: -6.8093
Max Act: 6.0905. Min Act: -0.1700
Data Index: 7612837 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19