Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2340. Min Range: -8.2340
Max Act: 8.2340. Min Act: -0.1700
Data Index: 1462399 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2340. Min Range: -8.2340
Max Act: 8.2340. Min Act: -0.1700
Data Index: 150446 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2340. Min Range: -8.2340
Max Act: 8.1090. Min Act: -0.1700
Data Index: 1812137 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2340. Min Range: -8.2340
Max Act: 8.1090. Min Act: -0.1700
Data Index: 1470493 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.9215. Min Act: -0.1700
Data Index: 4857077 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.9215. Min Act: -0.1700
Data Index: 1571844 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.9215. Min Act: -0.1700
Data Index: 4686168 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.9215. Min Act: -0.1700
Data Index: 1686654 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.8590. Min Act: -0.1700
Data Index: 5422688 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.8590. Min Act: -0.1700
Data Index: 2043500 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.7965. Min Act: -0.1700
Data Index: 1707312 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.6715. Min Act: -0.1700
Data Index: 84608 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.6715. Min Act: -0.1700
Data Index: 437364 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.5465. Min Act: -0.1700
Data Index: 4863771 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.6090. Min Act: -0.1700
Data Index: 4189112 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.6090. Min Act: -0.1700
Data Index: 8699868 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.6090. Min Act: -0.1700
Data Index: 5224525 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.5465. Min Act: -0.1700
Data Index: 3017660 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.5465. Min Act: -0.1700
Data Index: 2256978 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2340. Min Range: -8.2340
Max Act: 7.5465. Min Act: -0.1700
Data Index: 3776346 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19