Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0668. Min Range: -3.0668
Max Act: 3.0668. Min Act: -0.1700
Data Index: 6512542 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0668. Min Range: -3.0668
Max Act: 3.0352. Min Act: -0.1699
Data Index: 4456989 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.9404. Min Act: -0.1700
Data Index: 2726838 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.9245. Min Act: -0.1700
Data Index: 1022559 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.9087. Min Act: -0.1700
Data Index: 5256545 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8928. Min Act: -0.1700
Data Index: 914573 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8928. Min Act: -0.1700
Data Index: 2582053 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8928. Min Act: -0.1700
Data Index: 3808165 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8928. Min Act: -0.1700
Data Index: 2193544 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8928. Min Act: -0.1700
Data Index: 2957548 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8611. Min Act: -0.1700
Data Index: 7305092 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8770. Min Act: -0.1700
Data Index: 572578 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8770. Min Act: -0.1700
Data Index: 2713867 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8770. Min Act: -0.1700
Data Index: 3417889 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8770. Min Act: -0.1700
Data Index: 6968800 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8770. Min Act: -0.1700
Data Index: 4529571 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8611. Min Act: -0.1700
Data Index: 4457808 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8611. Min Act: -0.1700
Data Index: 108080 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8452. Min Act: -0.1700
Data Index: 2056603 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0668. Min Range: -3.0668
Max Act: 2.8611. Min Act: -0.1700
Data Index: 6315635 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19