Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.2734. Min Act: -0.1700
Data Index: 7093096 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.1948. Min Act: -0.1700
Data Index: 1484522 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.0846. Min Act: -0.1700
Data Index: 1655166 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.0688. Min Act: -0.1700
Data Index: 407771 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.0688. Min Act: -0.1700
Data Index: 3478532 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.0373. Min Act: -0.1700
Data Index: 6761103 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.0057. Min Act: -0.1700
Data Index: 7698009 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2734. Min Range: -3.2734
Max Act: 3.0057. Min Act: -0.1700
Data Index: 7131046 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9899. Min Act: -0.1700
Data Index: 7183016 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9740. Min Act: -0.1700
Data Index: 8020076 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9740. Min Act: -0.1700
Data Index: 5088491 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9582. Min Act: -0.1700
Data Index: 7742961 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9582. Min Act: -0.1700
Data Index: 5209510 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9424. Min Act: -0.1700
Data Index: 7451484 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9424. Min Act: -0.1700
Data Index: 2118288 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9424. Min Act: -0.1700
Data Index: 3149170 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9424. Min Act: -0.1700
Data Index: 3277653 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9424. Min Act: -0.1700
Data Index: 6166365 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9107. Min Act: -0.1700
Data Index: 2487649 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2734. Min Range: -3.2734
Max Act: 2.9266. Min Act: -0.1700
Data Index: 4140133 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19