Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 321 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2650. Min Range: -6.2650
Max Act: 6.2650. Min Act: -0.1700
Data Index: 7795787 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2650. Min Range: -6.2650
Max Act: 6.2025. Min Act: -0.1700
Data Index: 3607445 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2650. Min Range: -6.2650
Max Act: 6.1400. Min Act: -0.1700
Data Index: 8120986 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2650. Min Range: -6.2650
Max Act: 6.0775. Min Act: -0.1700
Data Index: 2458127 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.9525. Min Act: -0.1700
Data Index: 1029316 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.9837. Min Act: -0.1700
Data Index: 4748314 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.9837. Min Act: -0.1700
Data Index: 1345699 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.9212. Min Act: -0.1700
Data Index: 5394386 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.9212. Min Act: -0.1700
Data Index: 3417034 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.8900. Min Act: -0.1700
Data Index: 5403180 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.8587. Min Act: -0.1700
Data Index: 6954436 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.8587. Min Act: -0.1700
Data Index: 2171662 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.8587. Min Act: -0.1700
Data Index: 6287639 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.8587. Min Act: -0.1700
Data Index: 3031840 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.7962. Min Act: -0.1700
Data Index: 5202397 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.7962. Min Act: -0.1700
Data Index: 4762284 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.7962. Min Act: -0.1700
Data Index: 7980300 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.7962. Min Act: -0.1700
Data Index: 4201412 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.7650. Min Act: -0.1700
Data Index: 490338 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2650. Min Range: -6.2650
Max Act: 5.7337. Min Act: -0.1700
Data Index: 3985497 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19