Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5498 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.7662. Min Act: -0.1700
Data Index: 4784797 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.6412. Min Act: -0.1700
Data Index: 3810069 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.6412. Min Act: -0.1700
Data Index: 5902669 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.6412. Min Act: -0.1700
Data Index: 1290394 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.3912. Min Act: -0.1700
Data Index: 8259624 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.4224. Min Act: -0.1700
Data Index: 4346699 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.3599. Min Act: -0.1700
Data Index: 6907429 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.3287. Min Act: -0.1700
Data Index: 6794506 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2974. Min Act: -0.1700
Data Index: 5019181 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2974. Min Act: -0.1700
Data Index: 5643840 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2974. Min Act: -0.1700
Data Index: 1928933 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2662. Min Act: -0.1700
Data Index: 7716216 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2662. Min Act: -0.1700
Data Index: 1608898 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2662. Min Act: -0.1700
Data Index: 8000933 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2349. Min Act: -0.1700
Data Index: 1352054 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2037. Min Act: -0.1700
Data Index: 5577231 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.1724. Min Act: -0.1700
Data Index: 7232381 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2037. Min Act: -0.1700
Data Index: 7175698 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.2037. Min Act: -0.1700
Data Index: 2113788 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7662. Min Range: -6.7662
Max Act: 6.1724. Min Act: -0.1700
Data Index: 3103024 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19