Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.7403. Min Act: -0.1700
Data Index: 6380763 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.7403. Min Act: -0.1700
Data Index: 183115 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.7403. Min Act: -0.1700
Data Index: 1024879 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.6778. Min Act: -0.1700
Data Index: 4747089 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.5528. Min Act: -0.1700
Data Index: 383101 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.5528. Min Act: -0.1700
Data Index: 5884441 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.6153. Min Act: -0.1700
Data Index: 5871418 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.5528. Min Act: -0.1700
Data Index: 52389 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4903. Min Act: -0.1700
Data Index: 4148348 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4903. Min Act: -0.1700
Data Index: 7144493 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4903. Min Act: -0.1700
Data Index: 3183529 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4903. Min Act: -0.1700
Data Index: 1366237 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4278. Min Act: -0.1700
Data Index: 1314303 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4278. Min Act: -0.1700
Data Index: 1523792 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4278. Min Act: -0.1700
Data Index: 3186226 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.4278. Min Act: -0.1700
Data Index: 7523180 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.3653. Min Act: -0.1700
Data Index: 4015090 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.3653. Min Act: -0.1700
Data Index: 7860479 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.3653. Min Act: -0.1700
Data Index: 3951719 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7403. Min Range: -8.7403
Max Act: 8.3028. Min Act: -0.1700
Data Index: 1525362 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19