Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1020 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.2053. Min Act: -0.1700
Data Index: 3616054 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.2053. Min Act: -0.1700
Data Index: 110855 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.2053. Min Act: -0.1700
Data Index: 2718013 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2053. Min Range: -7.2053
Max Act: 7.1428. Min Act: -0.1700
Data Index: 1542297 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9865. Min Act: -0.1700
Data Index: 1739751 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9553. Min Act: -0.1700
Data Index: 4697231 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9865. Min Act: -0.1700
Data Index: 2408920 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9865. Min Act: -0.1700
Data Index: 1697280 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9553. Min Act: -0.1700
Data Index: 3679680 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8928. Min Act: -0.1700
Data Index: 2825584 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8928. Min Act: -0.1700
Data Index: 3679685 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9240. Min Act: -0.1700
Data Index: 6562615 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.9240. Min Act: -0.1700
Data Index: 7541350 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8928. Min Act: -0.1700
Data Index: 7196661 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8615. Min Act: -0.1700
Data Index: 4649380 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8615. Min Act: -0.1700
Data Index: 635544 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8303. Min Act: -0.1700
Data Index: 5568631 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8303. Min Act: -0.1700
Data Index: 5017838 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.8615. Min Act: -0.1700
Data Index: 620538 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2053. Min Range: -7.2053
Max Act: 6.7990. Min Act: -0.1700
Data Index: 1088076 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19