Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4608 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3403. Min Range: -8.3403
Max Act: 8.3403. Min Act: -0.1700
Data Index: 6053682 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3403. Min Range: -8.3403
Max Act: 8.2153. Min Act: -0.1700
Data Index: 3305750 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3403. Min Range: -8.3403
Max Act: 8.1528. Min Act: -0.1700
Data Index: 2673937 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3403. Min Range: -8.3403
Max Act: 8.1528. Min Act: -0.1700
Data Index: 6080672 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.7778. Min Act: -0.1700
Data Index: 398737 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.7778. Min Act: -0.1700
Data Index: 4529425 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.7778. Min Act: -0.1700
Data Index: 7412736 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.7153. Min Act: -0.1700
Data Index: 4470779 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 7390683 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 4996522 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.6528. Min Act: -0.1700
Data Index: 787115 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.6215. Min Act: -0.1700
Data Index: 2602230 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5903. Min Act: -0.1700
Data Index: 1076414 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5903. Min Act: -0.1700
Data Index: 8761786 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5903. Min Act: -0.1700
Data Index: 4812398 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5590. Min Act: -0.1700
Data Index: 3863351 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5903. Min Act: -0.1700
Data Index: 5776954 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5590. Min Act: -0.1700
Data Index: 4654764 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.5278. Min Act: -0.1700
Data Index: 1764240 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3403. Min Range: -8.3403
Max Act: 7.4965. Min Act: -0.1700
Data Index: 1887914 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19