Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5739 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8690. Min Act: -0.1700
Data Index: 8234450 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8065. Min Act: -0.1700
Data Index: 3011289 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.7440. Min Act: -0.1700
Data Index: 7138650 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5565. Min Act: -0.1700
Data Index: 3669723 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4667752 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.4627. Min Act: -0.1700
Data Index: 2299860 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.4627. Min Act: -0.1700
Data Index: 2922925 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.4002. Min Act: -0.1700
Data Index: 8304061 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.3690. Min Act: -0.1700
Data Index: 7439133 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.3690. Min Act: -0.1700
Data Index: 2527659 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.3690. Min Act: -0.1700
Data Index: 966453 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.3065. Min Act: -0.1700
Data Index: 5882922 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2752. Min Act: -0.1700
Data Index: 7764377 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.3065. Min Act: -0.1700
Data Index: 6060462 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2752. Min Act: -0.1700
Data Index: 1406832 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2752. Min Act: -0.1700
Data Index: 194146 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2752. Min Act: -0.1700
Data Index: 6852979 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2752. Min Act: -0.1700
Data Index: 2709219 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 677909 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 3282585 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19