Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3234 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1153. Min Range: -8.1153
Max Act: 8.1153. Min Act: -0.1700
Data Index: 3143652 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.8653. Min Act: -0.1700
Data Index: 1688396 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.7403. Min Act: -0.1700
Data Index: 445176 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.7403. Min Act: -0.1700
Data Index: 4029868 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.7403. Min Act: -0.1700
Data Index: 4523816 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.7090. Min Act: -0.1700
Data Index: 1841253 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.5215. Min Act: -0.1700
Data Index: 172985 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.5215. Min Act: -0.1700
Data Index: 7761493 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.4903. Min Act: -0.1700
Data Index: 8806474 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.4903. Min Act: -0.1698
Data Index: 3875923 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.4903. Min Act: -0.1700
Data Index: 2919813 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.4590. Min Act: -0.1700
Data Index: 6690811 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.4278. Min Act: -0.1700
Data Index: 1824175 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.3965. Min Act: -0.1700
Data Index: 7222919 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.3340. Min Act: -0.1700
Data Index: 8033481 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.3653. Min Act: -0.1700
Data Index: 3508651 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.3340. Min Act: -0.1700
Data Index: 45738 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.3340. Min Act: -0.1700
Data Index: 5833579 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.3028. Min Act: -0.1700
Data Index: 1756886 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1153. Min Range: -8.1153
Max Act: 7.2715. Min Act: -0.1700
Data Index: 7312628 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19