Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.9009. Min Act: -0.1700
Data Index: 2870886 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.7133. Min Act: -0.1700
Data Index: 62985 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.6820. Min Act: -0.1700
Data Index: 901460 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.6507. Min Act: -0.1700
Data Index: 5925711 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.6507. Min Act: -0.1700
Data Index: 8235960 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.6507. Min Act: -0.1700
Data Index: 8211383 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.6507. Min Act: -0.1700
Data Index: 3538782 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5881. Min Act: -0.1700
Data Index: 5211158 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5881. Min Act: -0.1700
Data Index: 5032881 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5881. Min Act: -0.1700
Data Index: 3538779 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5881. Min Act: -0.1700
Data Index: 5925710 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5568. Min Act: -0.1700
Data Index: 2148343 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5568. Min Act: -0.1700
Data Index: 215851 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5568. Min Act: -0.1700
Data Index: 215852 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5255. Min Act: -0.1700
Data Index: 7171713 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5255. Min Act: -0.1700
Data Index: 5947035 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.5568. Min Act: -0.1700
Data Index: 482632 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.4942. Min Act: -0.1700
Data Index: 7905776 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.4942. Min Act: -0.1700
Data Index: 2404111 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9009. Min Range: -3.9009
Max Act: 3.4628. Min Act: -0.1700
Data Index: 3568569 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19