Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.6079. Min Act: -0.1700
Data Index: 5851137 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.5454. Min Act: -0.1700
Data Index: 3973182 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1923682 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.3579. Min Act: -0.1700
Data Index: 926037 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.3579. Min Act: -0.1700
Data Index: 432576 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.2954. Min Act: -0.1700
Data Index: 3765226 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.2329. Min Act: -0.1700
Data Index: 1974162 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.2642. Min Act: -0.1700
Data Index: 8256337 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.2329. Min Act: -0.1700
Data Index: 7936548 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.2017. Min Act: -0.1700
Data Index: 3630410 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.1704. Min Act: -0.1700
Data Index: 1392087 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.1704. Min Act: -0.1700
Data Index: 2653933 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.0767. Min Act: -0.1700
Data Index: 5003287 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.0454. Min Act: -0.1700
Data Index: 4326689 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.0142. Min Act: -0.1700
Data Index: 5897545 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.0142. Min Act: -0.1700
Data Index: 5024957 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6079. Min Range: -5.6079
Max Act: 5.0142. Min Act: -0.1700
Data Index: 2176656 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6079. Min Range: -5.6079
Max Act: 4.9829. Min Act: -0.1700
Data Index: 2182810 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6079. Min Range: -5.6079
Max Act: 4.9829. Min Act: -0.1700
Data Index: 6531174 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6079. Min Range: -5.6079
Max Act: 4.9829. Min Act: -0.1700
Data Index: 5375472 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19