Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.5655. Min Act: -0.1700
Data Index: 5818264 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.4718. Min Act: -0.1700
Data Index: 1052884 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.4093. Min Act: -0.1700
Data Index: 7752885 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3780. Min Act: -0.1700
Data Index: 2799611 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3780. Min Act: -0.1700
Data Index: 3529829 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3780. Min Act: -0.1700
Data Index: 6474723 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5787338 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3468. Min Act: -0.1700
Data Index: 17426 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3468. Min Act: -0.1700
Data Index: 5508731 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3155. Min Act: -0.1700
Data Index: 5148260 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3155. Min Act: -0.1700
Data Index: 4508967 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2843. Min Act: -0.1700
Data Index: 3278812 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2843. Min Act: -0.1700
Data Index: 2285528 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2843. Min Act: -0.1700
Data Index: 1140188 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.3155. Min Act: -0.1700
Data Index: 6509155 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2530. Min Act: -0.1700
Data Index: 7578510 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3603242 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2530. Min Act: -0.1700
Data Index: 38586 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.2218. Min Act: -0.1700
Data Index: 3930840 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5655. Min Range: -5.5655
Max Act: 5.1905. Min Act: -0.1700
Data Index: 3907418 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19