Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2300 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.8965. Min Act: -0.1700
Data Index: 3173848 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.7715. Min Act: -0.1700
Data Index: 3863094 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.5840. Min Act: -0.1700
Data Index: 1716753 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.5840. Min Act: -0.1700
Data Index: 7603230 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.5215. Min Act: -0.1700
Data Index: 1315949 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 1024352 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.4590. Min Act: -0.1700
Data Index: 1269738 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.4590. Min Act: -0.1700
Data Index: 5806252 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 1596876 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3340. Min Act: -0.1700
Data Index: 8127879 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 376247 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 744829 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 3692869 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 4770088 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 5267811 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3340. Min Act: -0.1700
Data Index: 7443546 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3965. Min Act: -0.1700
Data Index: 5612208 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3340. Min Act: -0.1700
Data Index: 8127889 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.3340. Min Act: -0.1700
Data Index: 4659942 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8965. Min Range: -8.8965
Max Act: 8.2715. Min Act: -0.1700
Data Index: 1068647 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19