Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0092. Min Range: -9.0092
Max Act: 9.0092. Min Act: -0.1700
Data Index: 6137674 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0092. Min Range: -9.0092
Max Act: 8.3842. Min Act: -0.1700
Data Index: 4717833 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0092. Min Range: -9.0092
Max Act: 8.2592. Min Act: -0.1700
Data Index: 2458686 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0092. Min Range: -9.0092
Max Act: 8.1342. Min Act: -0.1700
Data Index: 28713 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0092. Min Range: -9.0092
Max Act: 8.0717. Min Act: -0.1700
Data Index: 699174 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 3243792 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 1902416 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 8289779 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 3749922 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 8437395 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 1563309 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8842. Min Act: -0.1700
Data Index: 5911086 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8842. Min Act: -0.1700
Data Index: 8328861 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.9467. Min Act: -0.1700
Data Index: 6495379 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8217. Min Act: -0.1700
Data Index: 4970618 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8217. Min Act: -0.1700
Data Index: 212188 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8217. Min Act: -0.1700
Data Index: 4760599 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8217. Min Act: -0.1700
Data Index: 2148341 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.8842. Min Act: -0.1700
Data Index: 7905775 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0092. Min Range: -9.0092
Max Act: 7.7592. Min Act: -0.1700
Data Index: 1811542 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19