Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3731 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.2672. Min Act: -0.1700
Data Index: 1448426 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.2176. Min Act: -0.1700
Data Index: 4353876 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.2176. Min Act: -0.1700
Data Index: 8455303 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1844. Min Act: -0.1700
Data Index: 5791629 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1844. Min Act: -0.1700
Data Index: 3278433 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1844. Min Act: -0.1700
Data Index: 4120415 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 5867628 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 8700773 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 1859643 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 8549937 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 4515791 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 2710818 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1699
Data Index: 844053 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1844. Min Act: -0.1700
Data Index: 6227152 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1678. Min Act: -0.1700
Data Index: 4353875 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1511. Min Act: -0.1700
Data Index: 6877680 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1345. Min Act: -0.1700
Data Index: 6594832 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1511. Min Act: -0.1700
Data Index: 2572611 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1511. Min Act: -0.1700
Data Index: 2474540 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2672. Min Range: -2.2672
Max Act: 2.1511. Min Act: -0.1700
Data Index: 3827309 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19