Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2610 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.7431. Min Act: -0.1700
Data Index: 8297487 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.6181. Min Act: -0.1700
Data Index: 2923319 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.4306. Min Act: -0.1700
Data Index: 5825781 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.4306. Min Act: -0.1700
Data Index: 5583852 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.4306. Min Act: -0.1700
Data Index: 7793499 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.4306. Min Act: -0.1700
Data Index: 210747 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.3681. Min Act: -0.1700
Data Index: 4607060 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.3681. Min Act: -0.1700
Data Index: 4263909 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.3056. Min Act: -0.1700
Data Index: 6836989 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.2431. Min Act: -0.1700
Data Index: 8073528 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1806. Min Act: -0.1700
Data Index: 5140778 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.2431. Min Act: -0.1700
Data Index: 5748518 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1806. Min Act: -0.1700
Data Index: 3405372 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1806. Min Act: -0.1700
Data Index: 4878306 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.2431. Min Act: -0.1700
Data Index: 8309557 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1181. Min Act: -0.1700
Data Index: 4177771 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1181. Min Act: -0.1700
Data Index: 1398763 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1181. Min Act: -0.1700
Data Index: 2488768 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1181. Min Act: -0.1700
Data Index: 3885193 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7431. Min Range: -8.7431
Max Act: 8.1181. Min Act: -0.1700
Data Index: 8290206 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19