Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0788. Min Range: -11.0788
Max Act: 11.0788. Min Act: -0.1700
Data Index: 6642974 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0788. Min Range: -11.0788
Max Act: 11.0163. Min Act: -0.1700
Data Index: 1046010 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0788. Min Range: -11.0788
Max Act: 10.0163. Min Act: -0.1700
Data Index: 7811697 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0788. Min Range: -11.0788
Max Act: 10.0163. Min Act: -0.1700
Data Index: 5069361 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.8913. Min Act: -0.1700
Data Index: 7704170 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.8913. Min Act: -0.1700
Data Index: 2586753 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.8288. Min Act: -0.1700
Data Index: 3270780 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.8288. Min Act: -0.1700
Data Index: 8711159 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.8288. Min Act: -0.1700
Data Index: 3998757 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.7663. Min Act: -0.1700
Data Index: 128225 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.7663. Min Act: -0.1700
Data Index: 7919094 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.7038. Min Act: -0.1700
Data Index: 4266221 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.6413. Min Act: -0.1700
Data Index: 3987558 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.6413. Min Act: -0.1700
Data Index: 6273829 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.6413. Min Act: -0.1700
Data Index: 6448421 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.5788. Min Act: -0.1700
Data Index: 6643185 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.5788. Min Act: -0.1700
Data Index: 623014 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.4538. Min Act: -0.1700
Data Index: 1910675 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.4538. Min Act: -0.1700
Data Index: 2284855 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0788. Min Range: -11.0788
Max Act: 9.4538. Min Act: -0.1700
Data Index: 1287512 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19