Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1623. Min Range: -6.1623
Max Act: 6.1623. Min Act: -0.1700
Data Index: 3969386 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1623. Min Range: -6.1623
Max Act: 6.0373. Min Act: -0.1700
Data Index: 1259765 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.7873. Min Act: -0.1700
Data Index: 2630127 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.7561. Min Act: -0.1700
Data Index: 3124905 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.7248. Min Act: -0.1700
Data Index: 6913293 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.6936. Min Act: -0.1700
Data Index: 7248570 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.6936. Min Act: -0.1700
Data Index: 3126278 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.6623. Min Act: -0.1700
Data Index: 2590617 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.6623. Min Act: -0.1700
Data Index: 3746648 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5998. Min Act: -0.1700
Data Index: 63059 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5998. Min Act: -0.1700
Data Index: 7255176 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5686. Min Act: -0.1700
Data Index: 8498484 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5686. Min Act: -0.1700
Data Index: 3190364 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5373. Min Act: -0.1700
Data Index: 2688700 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5061. Min Act: -0.1700
Data Index: 109763 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5061. Min Act: -0.1700
Data Index: 8480990 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.5061. Min Act: -0.1700
Data Index: 4153564 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.4748. Min Act: -0.1700
Data Index: 8392178 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.4436. Min Act: -0.1700
Data Index: 7201474 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1623. Min Range: -6.1623
Max Act: 5.4436. Min Act: -0.1700
Data Index: 470973 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19