Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.3423. Min Act: -0.1700
Data Index: 7148170 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.2798. Min Act: -0.1700
Data Index: 5367840 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.2173. Min Act: -0.1700
Data Index: 895563 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.2485. Min Act: -0.1700
Data Index: 1987000 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.2173. Min Act: -0.1700
Data Index: 2383643 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.1860. Min Act: -0.1700
Data Index: 3767069 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.1548. Min Act: -0.1700
Data Index: 6522910 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0923. Min Act: -0.1700
Data Index: 7270531 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0923. Min Act: -0.1700
Data Index: 8193640 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0923. Min Act: -0.1700
Data Index: 2463881 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0923. Min Act: -0.1700
Data Index: 6309592 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0610. Min Act: -0.1700
Data Index: 4304483 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0610. Min Act: -0.1700
Data Index: 8520773 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0610. Min Act: -0.1700
Data Index: 8619609 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0610. Min Act: -0.1700
Data Index: 7213332 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0610. Min Act: -0.1700
Data Index: 3086063 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0298. Min Act: -0.1700
Data Index: 975287 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0298. Min Act: -0.1700
Data Index: 5498680 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0298. Min Act: -0.1700
Data Index: 3958266 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3423. Min Range: -5.3423
Max Act: 5.0298. Min Act: -0.1700
Data Index: 5659485 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19