Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.8484. Min Act: -0.1700
Data Index: 8533930 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7546. Min Act: -0.1700
Data Index: 7045419 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7546. Min Act: -0.1700
Data Index: 6958621 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 7461375 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4859944 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 4968766 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.7234. Min Act: -0.1700
Data Index: 2902014 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6921. Min Act: -0.1700
Data Index: 2006799 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6921. Min Act: -0.1700
Data Index: 1328722 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6296. Min Act: -0.1700
Data Index: 2288759 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.6296. Min Act: -0.1700
Data Index: 8551568 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 1215402 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 7145097 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 2041479 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5984. Min Act: -0.1700
Data Index: 8171203 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5359. Min Act: -0.1700
Data Index: 2312199 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 755135 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 6771319 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5359. Min Act: -0.1700
Data Index: 2155354 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8484. Min Range: -6.8484
Max Act: 6.5671. Min Act: -0.1700
Data Index: 7394972 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19