Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.9513. Min Act: -0.1700
Data Index: 2598058 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.8575. Min Act: -0.1700
Data Index: 731559 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.8263. Min Act: -0.1700
Data Index: 4766569 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7950. Min Act: -0.1700
Data Index: 5976921 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3205488 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7638. Min Act: -0.1700
Data Index: 6845951 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7638. Min Act: -0.1700
Data Index: 3443673 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7638. Min Act: -0.1700
Data Index: 130132 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7638. Min Act: -0.1700
Data Index: 717958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 6368805 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 8448372 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 3779885 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 8255552 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1698
Data Index: 613781 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 2378886 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 1890001 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7013. Min Act: -0.1700
Data Index: 7681311 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7013. Min Act: -0.1700
Data Index: 1857910 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7325. Min Act: -0.1700
Data Index: 4696792 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9513. Min Range: -5.9513
Max Act: 5.7013. Min Act: -0.1700
Data Index: 4121262 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19