Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 418 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.5451. Min Act: -0.1700
Data Index: 2001269 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.4514. Min Act: -0.1700
Data Index: 3923760 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.4201. Min Act: -0.1700
Data Index: 5317377 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.2951. Min Act: -0.1700
Data Index: 8693737 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.2014. Min Act: -0.1700
Data Index: 6347718 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.2014. Min Act: -0.1700
Data Index: 3497821 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.2014. Min Act: -0.1700
Data Index: 2793305 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.2014. Min Act: -0.1700
Data Index: 804434 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.1701. Min Act: -0.1700
Data Index: 7110960 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.1389. Min Act: -0.1700
Data Index: 1119265 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.1076. Min Act: -0.1700
Data Index: 4824672 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.1076. Min Act: -0.1700
Data Index: 2538837 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.1076. Min Act: -0.1700
Data Index: 535138 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.1076. Min Act: -0.1700
Data Index: 3639351 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0764. Min Act: -0.1700
Data Index: 2397693 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0764. Min Act: -0.1700
Data Index: 1655171 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 7214603 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 7690258 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5451. Min Range: -7.5451
Max Act: 7.0451. Min Act: -0.1700
Data Index: 7208189 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5451. Min Range: -7.5451
Max Act: 6.9826. Min Act: -0.1700
Data Index: 2962969 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19