Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 505 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.9705. Min Act: -0.1700
Data Index: 6186407 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.8142. Min Act: -0.1700
Data Index: 2463585 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.7830. Min Act: -0.1700
Data Index: 6182623 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.7830. Min Act: -0.1700
Data Index: 8449829 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.7517. Min Act: -0.1698
Data Index: 5539034 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6892. Min Act: -0.1700
Data Index: 3492117 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6267. Min Act: -0.1700
Data Index: 5870961 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6580. Min Act: -0.1700
Data Index: 8814572 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6267. Min Act: -0.1700
Data Index: 7505416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6267. Min Act: -0.1700
Data Index: 7207523 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6267. Min Act: -0.1700
Data Index: 1483147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.6267. Min Act: -0.1700
Data Index: 65413 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 7465845 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 4714038 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 2994925 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 7012251 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 2231853 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 5846583 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5955. Min Act: -0.1700
Data Index: 589742 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9705. Min Range: -5.9705
Max Act: 5.5642. Min Act: -0.1700
Data Index: 5710081 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19