Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0723. Min Act: -0.1700
Data Index: 2839262 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0565. Min Act: -0.1700
Data Index: 1719565 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0408. Min Act: -0.1700
Data Index: 2278498 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0250. Min Act: -0.1700
Data Index: 3552672 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0408. Min Act: -0.1700
Data Index: 682106 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0250. Min Act: -0.1700
Data Index: 2163005 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0250. Min Act: -0.1700
Data Index: 4420141 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0250. Min Act: -0.1700
Data Index: 6672336 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0250. Min Act: -0.1700
Data Index: 7738846 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0250. Min Act: -0.1700
Data Index: 594433 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 7487876 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 878216 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 7738847 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 6594105 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 6020758 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.9934. Min Act: -0.1700
Data Index: 5659741 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 4687369 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0723. Min Range: -3.0723
Max Act: 3.0092. Min Act: -0.1700
Data Index: 1858948 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.9934. Min Act: -0.1700
Data Index: 4366007 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0723. Min Range: -3.0723
Max Act: 2.9934. Min Act: -0.1700
Data Index: 6675896 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19