Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 738 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0836. Min Range: -7.0836
Max Act: 7.0836. Min Act: -0.1700
Data Index: 2672400 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.9899. Min Act: -0.1700
Data Index: 3709008 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.8961. Min Act: -0.1700
Data Index: 4408616 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7711. Min Act: -0.1700
Data Index: 6570888 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7399. Min Act: -0.1700
Data Index: 1203656 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1214523 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7086. Min Act: -0.1700
Data Index: 3977931 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7399. Min Act: -0.1700
Data Index: 7854498 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7086. Min Act: -0.1700
Data Index: 3511512 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.7086. Min Act: -0.1700
Data Index: 1550576 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.6774. Min Act: -0.1700
Data Index: 3313846 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.6149. Min Act: -0.1700
Data Index: 8592175 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.5836. Min Act: -0.1700
Data Index: 8241876 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.5211. Min Act: -0.1700
Data Index: 7854551 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.4899. Min Act: -0.1700
Data Index: 1385175 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.4586. Min Act: -0.1700
Data Index: 8466207 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.4899. Min Act: -0.1700
Data Index: 3656021 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.4899. Min Act: -0.1700
Data Index: 2339023 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.4586. Min Act: -0.1700
Data Index: 551924 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0836. Min Range: -7.0836
Max Act: 6.4899. Min Act: -0.1700
Data Index: 6978427 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19