Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5589 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.8473. Min Act: -0.1700
Data Index: 1509165 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.7535. Min Act: -0.1700
Data Index: 4621983 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.7535. Min Act: -0.1700
Data Index: 6993865 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.7223. Min Act: -0.1700
Data Index: 6571399 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.5973. Min Act: -0.1700
Data Index: 2724418 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.5660. Min Act: -0.1700
Data Index: 8011566 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.5348. Min Act: -0.1700
Data Index: 1536956 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.5035. Min Act: -0.1700
Data Index: 6140489 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.5035. Min Act: -0.1700
Data Index: 1434696 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.4410. Min Act: -0.1700
Data Index: 5369077 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.4410. Min Act: -0.1700
Data Index: 3897758 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3785. Min Act: -0.1700
Data Index: 1015092 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 7137872 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 6101679 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 1495646 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 6003976 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3473. Min Act: -0.1700
Data Index: 7798006 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3160. Min Act: -0.1700
Data Index: 3291612 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3160. Min Act: -0.1700
Data Index: 6293173 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8473. Min Range: -6.8473
Max Act: 6.3160. Min Act: -0.1700
Data Index: 6112240 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19