Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 522 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1481. Min Range: -8.1481
Max Act: 8.1481. Min Act: -0.1700
Data Index: 5939843 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.8356. Min Act: -0.1700
Data Index: 365287 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7731. Min Act: -0.1700
Data Index: 6894604 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7731. Min Act: -0.1700
Data Index: 2966589 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7731. Min Act: -0.1700
Data Index: 2835848 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7419. Min Act: -0.1700
Data Index: 5287431 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7419. Min Act: -0.1700
Data Index: 2759924 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7731. Min Act: -0.1700
Data Index: 7969028 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.7106. Min Act: -0.1700
Data Index: 8123917 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.6794. Min Act: -0.1700
Data Index: 5864543 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.6794. Min Act: -0.1700
Data Index: 2909078 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.6794. Min Act: -0.1700
Data Index: 7025619 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.6169. Min Act: -0.1700
Data Index: 1137751 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.5856. Min Act: -0.1700
Data Index: 7908609 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.5231. Min Act: -0.1700
Data Index: 2171192 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.4919. Min Act: -0.1700
Data Index: 5221429 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.5231. Min Act: -0.1700
Data Index: 4349053 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.4919. Min Act: -0.1700
Data Index: 4548528 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.4919. Min Act: -0.1700
Data Index: 2312277 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1481. Min Range: -8.1481
Max Act: 7.4919. Min Act: -0.1700
Data Index: 8660023 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19