Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.6486. Min Act: -0.1700
Data Index: 6211601 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.5236. Min Act: -0.1700
Data Index: 5654013 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.4923. Min Act: -0.1700
Data Index: 421796 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.4923. Min Act: -0.1700
Data Index: 1392161 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.4298. Min Act: -0.1700
Data Index: 6337995 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.3986. Min Act: -0.1700
Data Index: 5336453 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.3361. Min Act: -0.1700
Data Index: 916673 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.3361. Min Act: -0.1700
Data Index: 7772086 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.2736. Min Act: -0.1700
Data Index: 5208756 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.2423. Min Act: -0.1700
Data Index: 8807980 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.2736. Min Act: -0.1700
Data Index: 5573032 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.2111. Min Act: -0.1700
Data Index: 3790624 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.2111. Min Act: -0.1700
Data Index: 2135592 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.2111. Min Act: -0.1700
Data Index: 8396565 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.1798. Min Act: -0.1700
Data Index: 2781270 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.1798. Min Act: -0.1700
Data Index: 7577868 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.1798. Min Act: -0.1700
Data Index: 3424303 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.1486. Min Act: -0.1700
Data Index: 3087646 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.0861. Min Act: -0.1700
Data Index: 6550082 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6486. Min Range: -5.6486
Max Act: 5.1173. Min Act: -0.1700
Data Index: 7089100 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19