Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 872 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1442. Min Range: -3.1442
Max Act: 3.1442. Min Act: -0.1700
Data Index: 3275576 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1442. Min Range: -3.1442
Max Act: 3.1285. Min Act: -0.1700
Data Index: 1431920 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1442. Min Range: -3.1442
Max Act: 3.0812. Min Act: -0.1700
Data Index: 6621677 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1442. Min Range: -3.1442
Max Act: 3.0181. Min Act: -0.1700
Data Index: 1090715 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9864. Min Act: -0.1700
Data Index: 374430 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9706. Min Act: -0.1700
Data Index: 2454516 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9706. Min Act: -0.1700
Data Index: 3796404 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9706. Min Act: -0.1700
Data Index: 999667 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9231. Min Act: -0.1700
Data Index: 3769113 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9231. Min Act: -0.1700
Data Index: 5352969 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9231. Min Act: -0.1700
Data Index: 6146144 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9073. Min Act: -0.1700
Data Index: 4073131 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9073. Min Act: -0.1700
Data Index: 6402670 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9073. Min Act: -0.1700
Data Index: 7521959 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.8914. Min Act: -0.1700
Data Index: 490387 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.9073. Min Act: -0.1700
Data Index: 1200478 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.8597. Min Act: -0.1700
Data Index: 6786049 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.8756. Min Act: -0.1700
Data Index: 2937847 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.8756. Min Act: -0.1700
Data Index: 1528039 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1442. Min Range: -3.1442
Max Act: 2.8756. Min Act: -0.1700
Data Index: 1748023 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19