Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3926 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.7615. Min Act: -0.1700
Data Index: 110368 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.6676. Min Act: -0.1700
Data Index: 4153988 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.6520. Min Act: -0.1700
Data Index: 3481101 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.6207. Min Act: -0.1700
Data Index: 2619719 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5894. Min Act: -0.1700
Data Index: 3692338 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5737. Min Act: -0.1700
Data Index: 6383784 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5581. Min Act: -0.1700
Data Index: 7211019 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5894. Min Act: -0.1700
Data Index: 3697311 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5737. Min Act: -0.1700
Data Index: 7228197 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5424. Min Act: -0.1700
Data Index: 971845 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5737. Min Act: -0.1700
Data Index: 8520379 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5424. Min Act: -0.1700
Data Index: 283857 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5424. Min Act: -0.1700
Data Index: 5406463 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5424. Min Act: -0.1700
Data Index: 4042812 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5111. Min Act: -0.1700
Data Index: 7164103 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5268. Min Act: -0.1700
Data Index: 359488 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.5268. Min Act: -0.1700
Data Index: 2860036 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.4954. Min Act: -0.1700
Data Index: 6320507 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.4954. Min Act: -0.1700
Data Index: 5850364 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7615. Min Range: -3.7615
Max Act: 3.4798. Min Act: -0.1700
Data Index: 1708666 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19