Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6335 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.4251. Min Act: -0.1700
Data Index: 650372 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.3001. Min Act: -0.1700
Data Index: 5174763 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.3001. Min Act: -0.1700
Data Index: 3180665 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.3001. Min Act: -0.1700
Data Index: 8443754 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.2689. Min Act: -0.1700
Data Index: 4962625 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.2376. Min Act: -0.1700
Data Index: 8118281 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.2376. Min Act: -0.1700
Data Index: 8782911 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.1751. Min Act: -0.1700
Data Index: 2474628 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.1751. Min Act: -0.1700
Data Index: 7392569 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.1751. Min Act: -0.1700
Data Index: 184870 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.1439. Min Act: -0.1700
Data Index: 3084819 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.1751. Min Act: -0.1700
Data Index: 8782910 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.0814. Min Act: -0.1700
Data Index: 5997264 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.0501. Min Act: -0.1700
Data Index: 3560868 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.0501. Min Act: -0.1700
Data Index: 807517 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9876. Min Act: -0.1700
Data Index: 8671657 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.0189. Min Act: -0.1700
Data Index: 6882535 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9876. Min Act: -0.1700
Data Index: 7112017 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9564. Min Act: -0.1700
Data Index: 1686195 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9564. Min Act: -0.1700
Data Index: 6923058 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19