Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.6399. Min Act: -0.1700
Data Index: 2180517 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.6086. Min Act: -0.1700
Data Index: 3950973 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.5774. Min Act: -0.1700
Data Index: 5039270 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.5149. Min Act: -0.1700
Data Index: 5133677 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.4836. Min Act: -0.1700
Data Index: 3296513 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.5149. Min Act: -0.1700
Data Index: 5115102 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.3586. Min Act: -0.1700
Data Index: 8225779 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.3586. Min Act: -0.1700
Data Index: 6680260 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.2336. Min Act: -0.1700
Data Index: 5294626 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.1711. Min Act: -0.1700
Data Index: 5007355 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.1711. Min Act: -0.1700
Data Index: 461396 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.1711. Min Act: -0.1700
Data Index: 592446 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.1086. Min Act: -0.1700
Data Index: 2354524 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.0774. Min Act: -0.1700
Data Index: 985878 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.0461. Min Act: -0.1700
Data Index: 4333127 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6399. Min Range: -7.6399
Max Act: 6.9836. Min Act: -0.1700
Data Index: 4101961 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6399. Min Range: -7.6399
Max Act: 7.0149. Min Act: -0.1700
Data Index: 2442754 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6399. Min Range: -7.6399
Max Act: 6.9836. Min Act: -0.1700
Data Index: 8089680 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6399. Min Range: -7.6399
Max Act: 6.9524. Min Act: -0.1700
Data Index: 1300663 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6399. Min Range: -7.6399
Max Act: 6.9524. Min Act: -0.1700
Data Index: 8831904 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19