Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 982 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5599. Min Range: -12.5599
Max Act: 12.5599. Min Act: -0.1700
Data Index: 8168364 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5599. Min Range: -12.5599
Max Act: 12.4974. Min Act: -0.1700
Data Index: 7972207 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5599. Min Range: -12.5599
Max Act: 12.3099. Min Act: -0.1700
Data Index: 1817625 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5599. Min Range: -12.5599
Max Act: 12.1224. Min Act: -0.1700
Data Index: 2467420 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5599. Min Range: -12.5599
Max Act: 12.1224. Min Act: -0.1700
Data Index: 5876610 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9974. Min Act: -0.1700
Data Index: 5195932 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9974. Min Act: -0.1700
Data Index: 5471939 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9974. Min Act: -0.1700
Data Index: 7029628 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9349. Min Act: -0.1700
Data Index: 1197705 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9349. Min Act: -0.1700
Data Index: 4470464 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9349. Min Act: -0.1700
Data Index: 8294099 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9349. Min Act: -0.1700
Data Index: 1062728 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8724. Min Act: -0.1700
Data Index: 5782576 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8724. Min Act: -0.1700
Data Index: 4627139 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8724. Min Act: -0.1700
Data Index: 6470160 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8724. Min Act: -0.1700
Data Index: 2962406 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.9349. Min Act: -0.1700
Data Index: 709226 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8724. Min Act: -0.1700
Data Index: 7406249 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8724. Min Act: -0.1700
Data Index: 6595837 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5599. Min Range: -12.5599
Max Act: 11.8099. Min Act: -0.1700
Data Index: 3051172 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19