Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.2603. Min Act: -0.1700
Data Index: 3736802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.2603. Min Act: -0.1700
Data Index: 4632039 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.2603. Min Act: -0.1700
Data Index: 8436678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.2603. Min Act: -0.1700
Data Index: 7745797 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.2603. Min Act: -0.1700
Data Index: 7855464 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.2106. Min Act: -0.1700
Data Index: 6235337 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1940. Min Act: -0.1700
Data Index: 2967860 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1774. Min Act: -0.1700
Data Index: 7282933 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1774. Min Act: -0.1700
Data Index: 8034980 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1774. Min Act: -0.1700
Data Index: 5742945 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1441. Min Act: -0.1700
Data Index: 5059591 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1441. Min Act: -0.1700
Data Index: 8195755 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1274. Min Act: -0.1700
Data Index: 6209990 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1107. Min Act: -0.1700
Data Index: 2408063 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.1107. Min Act: -0.1700
Data Index: 8143153 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.0940. Min Act: -0.1700
Data Index: 3663032 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.0772. Min Act: -0.1700
Data Index: 8143152 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.0940. Min Act: -0.1700
Data Index: 8143148 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.0940. Min Act: -0.1700
Data Index: 1389951 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2603. Min Range: -2.2603
Max Act: 2.0772. Min Act: -0.1700
Data Index: 246901 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19