Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1949. Min Range: -5.1949
Max Act: 5.1949. Min Act: -0.1700
Data Index: 2162559 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1949. Min Range: -5.1949
Max Act: 5.1012. Min Act: -0.1700
Data Index: 6443450 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1949. Min Range: -5.1949
Max Act: 5.0074. Min Act: -0.1700
Data Index: 6819756 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.9762. Min Act: -0.1700
Data Index: 3678969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.9449. Min Act: -0.1700
Data Index: 4150209 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.9449. Min Act: -0.1700
Data Index: 6064435 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.8824. Min Act: -0.1700
Data Index: 5704419 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.8512. Min Act: -0.1700
Data Index: 1800559 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.8199. Min Act: -0.1700
Data Index: 1880102 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.7887. Min Act: -0.1700
Data Index: 4563732 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.7887. Min Act: -0.1700
Data Index: 7286505 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.7574. Min Act: -0.1700
Data Index: 6714323 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6949. Min Act: -0.1700
Data Index: 4404801 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6949. Min Act: -0.1700
Data Index: 5682187 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6949. Min Act: -0.1700
Data Index: 2614518 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6637. Min Act: -0.1700
Data Index: 5304748 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6637. Min Act: -0.1700
Data Index: 1169071 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6637. Min Act: -0.1700
Data Index: 2727724 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6324. Min Act: -0.1700
Data Index: 2348975 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1949. Min Range: -5.1949
Max Act: 4.6324. Min Act: -0.1700
Data Index: 1394949 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19