Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.5606. Min Act: -0.1700
Data Index: 412587 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.3106. Min Act: -0.1700
Data Index: 3076510 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.3106. Min Act: -0.1700
Data Index: 1886458 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.1856. Min Act: -0.1700
Data Index: 2937254 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.1856. Min Act: -0.1700
Data Index: 5016757 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.1543. Min Act: -0.1700
Data Index: 5814351 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.1231. Min Act: -0.1700
Data Index: 8528477 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0606. Min Act: -0.1700
Data Index: 6148706 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0293. Min Act: -0.1700
Data Index: 7527581 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0293. Min Act: -0.1700
Data Index: 7254060 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5606. Min Range: -7.5606
Max Act: 6.9981. Min Act: -0.1700
Data Index: 8415005 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0606. Min Act: -0.1700
Data Index: 834285 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0293. Min Act: -0.1700
Data Index: 7311465 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5606. Min Range: -7.5606
Max Act: 6.9981. Min Act: -0.1700
Data Index: 1760336 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0293. Min Act: -0.1700
Data Index: 195507 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5606. Min Range: -7.5606
Max Act: 6.9668. Min Act: -0.1700
Data Index: 1738212 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5606. Min Range: -7.5606
Max Act: 7.0293. Min Act: -0.1700
Data Index: 1421108 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5606. Min Range: -7.5606
Max Act: 6.9668. Min Act: -0.1700
Data Index: 2051707 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5606. Min Range: -7.5606
Max Act: 6.9668. Min Act: -0.1700
Data Index: 3076495 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5606. Min Range: -7.5606
Max Act: 6.9668. Min Act: -0.1700
Data Index: 3610090 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19