Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4954. Min Act: -0.1700
Data Index: 7323966 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4642. Min Act: -0.1700
Data Index: 17507 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4642. Min Act: -0.1700
Data Index: 6178770 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 8785571 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 375374 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 6005791 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 1676758 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 682619 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 8630636 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 1451610 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 5892800 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 735094 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 5486679 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 1787257 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 5172829 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 920254 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 6694303 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 4509449 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4329. Min Act: -0.1700
Data Index: 7443122 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4954. Min Range: -7.4954
Max Act: 7.4017. Min Act: -0.1700
Data Index: 2157073 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19