Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.9855. Min Act: -0.1700
Data Index: 3524977 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.8917. Min Act: -0.1700
Data Index: 662732 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.8605. Min Act: -0.1700
Data Index: 4448497 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.8292. Min Act: -0.1700
Data Index: 7291380 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7980. Min Act: -0.1700
Data Index: 2412988 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.8292. Min Act: -0.1700
Data Index: 8632313 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.8292. Min Act: -0.1700
Data Index: 8110070 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7980. Min Act: -0.1700
Data Index: 6139857 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7667. Min Act: -0.1700
Data Index: 6263473 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7667. Min Act: -0.1700
Data Index: 8038793 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7980. Min Act: -0.1700
Data Index: 2905457 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7042. Min Act: -0.1700
Data Index: 3513409 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7355. Min Act: -0.1700
Data Index: 627097 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7355. Min Act: -0.1700
Data Index: 7356962 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7355. Min Act: -0.1700
Data Index: 2032053 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7355. Min Act: -0.1700
Data Index: 6760936 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7355. Min Act: -0.1700
Data Index: 1983115 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7042. Min Act: -0.1700
Data Index: 2813806 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7042. Min Act: -0.1700
Data Index: 1977733 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9855. Min Range: -4.9855
Max Act: 4.7355. Min Act: -0.1700
Data Index: 5220407 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19