Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.2802. Min Act: -0.1700
Data Index: 8565948 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.3115. Min Act: -0.1700
Data Index: 6030368 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.1240. Min Act: -0.1700
Data Index: 495530 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.1552. Min Act: -0.1700
Data Index: 1825595 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4967359 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0927. Min Act: -0.1700
Data Index: 2018491 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 7921355 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4278239 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 4278238 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 5803598 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 6019976 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 8024254 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 4301827 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0615. Min Act: -0.1700
Data Index: 348722 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0302. Min Act: -0.1700
Data Index: 381645 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3115. Min Range: -5.3115
Max Act: 4.9990. Min Act: -0.1700
Data Index: 5988708 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3115. Min Range: -5.3115
Max Act: 5.0302. Min Act: -0.1700
Data Index: 1088832 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3115. Min Range: -5.3115
Max Act: 4.9677. Min Act: -0.1700
Data Index: 7619785 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3115. Min Range: -5.3115
Max Act: 4.9365. Min Act: -0.1700
Data Index: 6203427 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3115. Min Range: -5.3115
Max Act: 4.9365. Min Act: -0.1700
Data Index: 2278648 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19