Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.3881. Min Act: -0.1700
Data Index: 2886339 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.3256. Min Act: -0.1700
Data Index: 201287 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2944. Min Act: -0.1700
Data Index: 1529721 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2944. Min Act: -0.1700
Data Index: 5091964 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2944. Min Act: -0.1700
Data Index: 8357496 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2631. Min Act: -0.1700
Data Index: 1804854 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2631. Min Act: -0.1700
Data Index: 5427670 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2944. Min Act: -0.1700
Data Index: 622833 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2318. Min Act: -0.1700
Data Index: 4259794 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2006. Min Act: -0.1700
Data Index: 7867428 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.1693. Min Act: -0.1700
Data Index: 2397376 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2006. Min Act: -0.1700
Data Index: 1804860 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2006. Min Act: -0.1700
Data Index: 4105893 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2006. Min Act: -0.1700
Data Index: 7446963 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2006. Min Act: -0.1700
Data Index: 777713 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.2006. Min Act: -0.1700
Data Index: 378855 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.1693. Min Act: -0.1700
Data Index: 4627898 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.1693. Min Act: -0.1700
Data Index: 1529722 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.1693. Min Act: -0.1700
Data Index: 6339991 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3881. Min Range: -4.3881
Max Act: 4.1693. Min Act: -0.1700
Data Index: 3403018 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19