Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4843 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.6847. Min Act: -0.1700
Data Index: 3543763 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.5285. Min Act: -0.1700
Data Index: 7797418 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.4972. Min Act: -0.1700
Data Index: 150574 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.4660. Min Act: -0.1700
Data Index: 1357181 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.4660. Min Act: -0.1700
Data Index: 1357183 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.4035. Min Act: -0.1700
Data Index: 3897497 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.4035. Min Act: -0.1700
Data Index: 3509969 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3722. Min Act: -0.1700
Data Index: 7065726 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3722. Min Act: -0.1700
Data Index: 5553713 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3722. Min Act: -0.1700
Data Index: 2803605 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3410. Min Act: -0.1700
Data Index: 4610509 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3410. Min Act: -0.1700
Data Index: 5503336 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3410. Min Act: -0.1700
Data Index: 8140771 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3410. Min Act: -0.1700
Data Index: 3559138 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.2785. Min Act: -0.1700
Data Index: 1691588 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.3097. Min Act: -0.1700
Data Index: 2315933 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.2472. Min Act: -0.1698
Data Index: 2081555 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.2472. Min Act: -0.1700
Data Index: 2990607 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.2472. Min Act: -0.1700
Data Index: 39717 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6847. Min Range: -5.6847
Max Act: 5.2472. Min Act: -0.1700
Data Index: 565780 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19