Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5265 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.4465. Min Act: -0.1700
Data Index: 3318744 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.3215. Min Act: -0.1700
Data Index: 2796640 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.2590. Min Act: -0.1700
Data Index: 7984364 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.2590. Min Act: -0.1700
Data Index: 2978465 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.1652. Min Act: -0.1700
Data Index: 5285574 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.1340. Min Act: -0.1700
Data Index: 3940135 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.1027. Min Act: -0.1700
Data Index: 6459780 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.0715. Min Act: -0.1700
Data Index: 493421 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.0402. Min Act: -0.1700
Data Index: 8251718 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.0090. Min Act: -0.1700
Data Index: 3876079 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4465. Min Range: -6.4465
Max Act: 6.0090. Min Act: -0.1700
Data Index: 4031789 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9465. Min Act: -0.1700
Data Index: 8433877 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9465. Min Act: -0.1700
Data Index: 6236434 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9465. Min Act: -0.1700
Data Index: 6394139 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9465. Min Act: -0.1700
Data Index: 4797586 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9152. Min Act: -0.1700
Data Index: 2481689 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9152. Min Act: -0.1700
Data Index: 544055 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.9152. Min Act: -0.1700
Data Index: 4677369 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.8527. Min Act: -0.1700
Data Index: 7953667 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4465. Min Range: -6.4465
Max Act: 5.8840. Min Act: -0.1700
Data Index: 3710610 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19