Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2026 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.7017. Min Act: -0.1700
Data Index: 7219130 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.6079. Min Act: -0.1700
Data Index: 8557453 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.5454. Min Act: -0.1700
Data Index: 7177760 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.5142. Min Act: -0.1700
Data Index: 3486859 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.5142. Min Act: -0.1700
Data Index: 5619772 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.4829. Min Act: -0.1700
Data Index: 2513870 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.4829. Min Act: -0.1700
Data Index: 8145611 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.3892. Min Act: -0.1700
Data Index: 5442409 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.3579. Min Act: -0.1700
Data Index: 5606901 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.3579. Min Act: -0.1700
Data Index: 2577513 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.3267. Min Act: -0.1700
Data Index: 8651757 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.3267. Min Act: -0.1700
Data Index: 2120856 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.2954. Min Act: -0.1700
Data Index: 2744506 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.2017. Min Act: -0.1700
Data Index: 2599368 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 2569489 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 7032489 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.1392. Min Act: -0.1700
Data Index: 690168 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.1392. Min Act: -0.1700
Data Index: 2374796 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.1079. Min Act: -0.1700
Data Index: 3386833 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7017. Min Range: -5.7017
Max Act: 5.1079. Min Act: -0.1700
Data Index: 167013 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19