Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4754 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4576. Min Range: -6.4576
Max Act: 6.4576. Min Act: -0.1700
Data Index: 3561429 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4576. Min Range: -6.4576
Max Act: 6.3013. Min Act: -0.1700
Data Index: 6803251 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4576. Min Range: -6.4576
Max Act: 6.0826. Min Act: -0.1700
Data Index: 1743212 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4576. Min Range: -6.4576
Max Act: 6.0826. Min Act: -0.1700
Data Index: 2454481 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4576. Min Range: -6.4576
Max Act: 6.0201. Min Act: -0.1700
Data Index: 1964762 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.8951. Min Act: -0.1700
Data Index: 7769750 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.8951. Min Act: -0.1700
Data Index: 8540123 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.8638. Min Act: -0.1700
Data Index: 3362893 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.8638. Min Act: -0.1700
Data Index: 6989214 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.8013. Min Act: -0.1700
Data Index: 8411393 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 2860051 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 3568308 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 1888433 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7388. Min Act: -0.1700
Data Index: 3762759 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 4426344 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7388. Min Act: -0.1700
Data Index: 8681817 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7388. Min Act: -0.1700
Data Index: 6786698 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7701. Min Act: -0.1700
Data Index: 1003898 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7388. Min Act: -0.1700
Data Index: 2014314 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4576. Min Range: -6.4576
Max Act: 5.7076. Min Act: -0.1700
Data Index: 5109752 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19