Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.9179. Min Act: -0.1700
Data Index: 5795660 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6679. Min Act: -0.1700
Data Index: 4240768 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6679. Min Act: -0.1700
Data Index: 4536969 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6679. Min Act: -0.1700
Data Index: 3496105 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6679. Min Act: -0.1700
Data Index: 8582167 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6366. Min Act: -0.1700
Data Index: 242449 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6366. Min Act: -0.1700
Data Index: 2437268 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6679. Min Act: -0.1700
Data Index: 651067 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6366. Min Act: -0.1700
Data Index: 3114895 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.6054. Min Act: -0.1700
Data Index: 5942542 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5429. Min Act: -0.1700
Data Index: 5796308 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5741. Min Act: -0.1700
Data Index: 912783 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5429. Min Act: -0.1700
Data Index: 2306522 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5429. Min Act: -0.1700
Data Index: 8153045 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5116. Min Act: -0.1700
Data Index: 3499519 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.4804. Min Act: -0.1700
Data Index: 2927004 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5116. Min Act: -0.1700
Data Index: 6085681 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5116. Min Act: -0.1700
Data Index: 1820742 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.5116. Min Act: -0.1700
Data Index: 7795091 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9179. Min Range: -4.9179
Max Act: 4.4804. Min Act: -0.1700
Data Index: 1063410 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19