Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5106. Min Range: -7.5106
Max Act: 7.5106. Min Act: -0.1700
Data Index: 197897 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5106. Min Range: -7.5106
Max Act: 7.3544. Min Act: -0.1700
Data Index: 2443884 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5106. Min Range: -7.5106
Max Act: 7.2606. Min Act: -0.1700
Data Index: 3100657 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5106. Min Range: -7.5106
Max Act: 7.0731. Min Act: -0.1700
Data Index: 2997386 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.9794. Min Act: -0.1700
Data Index: 5767498 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.9794. Min Act: -0.1700
Data Index: 1420415 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.9794. Min Act: -0.1700
Data Index: 8512420 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.9481. Min Act: -0.1700
Data Index: 3582816 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.9169. Min Act: -0.1700
Data Index: 6467023 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.9169. Min Act: -0.1700
Data Index: 4132508 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.8856. Min Act: -0.1700
Data Index: 4245521 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.8231. Min Act: -0.1700
Data Index: 8348911 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.8231. Min Act: -0.1700
Data Index: 3886338 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.8231. Min Act: -0.1700
Data Index: 4029702 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.8231. Min Act: -0.1700
Data Index: 1980533 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.7919. Min Act: -0.1700
Data Index: 8134930 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.7606. Min Act: -0.1700
Data Index: 8567615 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.7294. Min Act: -0.1700
Data Index: 2605640 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.6981. Min Act: -0.1700
Data Index: 4190687 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5106. Min Range: -7.5106
Max Act: 6.6981. Min Act: -0.1700
Data Index: 5045496 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19