Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.8903. Min Act: -0.1700
Data Index: 7088230 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.8586. Min Act: -0.1700
Data Index: 4795317 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.8586. Min Act: -0.1700
Data Index: 6650428 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.8427. Min Act: -0.1700
Data Index: 426643 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.8268. Min Act: -0.1700
Data Index: 2929851 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7790. Min Act: -0.1700
Data Index: 3765949 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7790. Min Act: -0.1700
Data Index: 3004617 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7471. Min Act: -0.1700
Data Index: 4877828 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7471. Min Act: -0.1700
Data Index: 4514346 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7311. Min Act: -0.1700
Data Index: 3270430 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7311. Min Act: -0.1700
Data Index: 6529023 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7151. Min Act: -0.1700
Data Index: 810804 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7151. Min Act: -0.1700
Data Index: 5486943 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.7151. Min Act: -0.1700
Data Index: 4463061 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.6991. Min Act: -0.1700
Data Index: 882678 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.6991. Min Act: -0.1700
Data Index: 4895510 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.6991. Min Act: -0.1700
Data Index: 3097854 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.6831. Min Act: -0.1700
Data Index: 1420754 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.6831. Min Act: -0.1700
Data Index: 861002 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8903. Min Range: -2.8903
Max Act: 2.6671. Min Act: -0.1700
Data Index: 3935957 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19