Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4735 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1799. Min Range: -7.1799
Max Act: 7.1799. Min Act: -0.1700
Data Index: 3753302 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1799. Min Range: -7.1799
Max Act: 7.0237. Min Act: -0.1700
Data Index: 1262596 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.9612. Min Act: -0.1700
Data Index: 3075393 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.8674. Min Act: -0.1700
Data Index: 7090113 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.8049. Min Act: -0.1700
Data Index: 4585985 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.7424. Min Act: -0.1700
Data Index: 7306250 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.7424. Min Act: -0.1700
Data Index: 6234243 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.6799. Min Act: -0.1700
Data Index: 3100550 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.7112. Min Act: -0.1700
Data Index: 2728965 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.6487. Min Act: -0.1700
Data Index: 2569829 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5862. Min Act: -0.1700
Data Index: 1361415 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5862. Min Act: -0.1700
Data Index: 2694762 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5549. Min Act: -0.1700
Data Index: 2948244 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5862. Min Act: -0.1700
Data Index: 984012 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5549. Min Act: -0.1700
Data Index: 4864425 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5862. Min Act: -0.1700
Data Index: 8412622 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5549. Min Act: -0.1700
Data Index: 7829557 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5237. Min Act: -0.1700
Data Index: 6083131 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.5549. Min Act: -0.1700
Data Index: 2227549 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1799. Min Range: -7.1799
Max Act: 6.4924. Min Act: -0.1700
Data Index: 5695353 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19