Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0490. Min Range: -4.0490
Max Act: 4.0490. Min Act: -0.1700
Data Index: 2278422 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.9240. Min Act: -0.1700
Data Index: 6114630 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.8927. Min Act: -0.1700
Data Index: 4265195 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.8614. Min Act: -0.1700
Data Index: 4167693 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.8614. Min Act: -0.1700
Data Index: 3100784 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.8301. Min Act: -0.1700
Data Index: 1132443 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.8301. Min Act: -0.1700
Data Index: 1473766 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.8301. Min Act: -0.1700
Data Index: 8652245 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.7832. Min Act: -0.1700
Data Index: 6827106 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.7676. Min Act: -0.1700
Data Index: 8204686 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.7363. Min Act: -0.1700
Data Index: 941397 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.7207. Min Act: -0.1700
Data Index: 1220918 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.7207. Min Act: -0.1700
Data Index: 58062 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6894. Min Act: -0.1700
Data Index: 1104478 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6737. Min Act: -0.1700
Data Index: 7083714 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6894. Min Act: -0.1700
Data Index: 7427118 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6894. Min Act: -0.1700
Data Index: 2288293 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6737. Min Act: -0.1700
Data Index: 7811350 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6894. Min Act: -0.1700
Data Index: 536789 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0490. Min Range: -4.0490
Max Act: 3.6581. Min Act: -0.1700
Data Index: 3379594 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19