Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1705. Min Range: -7.1705
Max Act: 7.1705. Min Act: -0.1700
Data Index: 1563566 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1705. Min Range: -7.1705
Max Act: 7.1080. Min Act: -0.1700
Data Index: 6384849 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1705. Min Range: -7.1705
Max Act: 7.0143. Min Act: -0.1700
Data Index: 482007 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.8893. Min Act: -0.1700
Data Index: 8694502 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.8268. Min Act: -0.1700
Data Index: 8170426 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.8268. Min Act: -0.1700
Data Index: 4614606 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7643. Min Act: -0.1700
Data Index: 6679246 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7643. Min Act: -0.1700
Data Index: 7438836 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7330. Min Act: -0.1700
Data Index: 821357 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7330. Min Act: -0.1700
Data Index: 8802167 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7018. Min Act: -0.1700
Data Index: 5191 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7018. Min Act: -0.1700
Data Index: 560979 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.7018. Min Act: -0.1700
Data Index: 7560703 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6393. Min Act: -0.1700
Data Index: 5936049 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6393. Min Act: -0.1700
Data Index: 6654296 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6393. Min Act: -0.1700
Data Index: 302998 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6080. Min Act: -0.1700
Data Index: 8651667 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6080. Min Act: -0.1700
Data Index: 3234759 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6080. Min Act: -0.1700
Data Index: 4763568 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1705. Min Range: -7.1705
Max Act: 6.6080. Min Act: -0.1700
Data Index: 2603107 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19