Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3277 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.5894. Min Act: -0.1700
Data Index: 1563685 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.2457. Min Act: -0.1700
Data Index: 8446069 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.1832. Min Act: -0.1700
Data Index: 921072 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.0894. Min Act: -0.1700
Data Index: 6104686 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.0582. Min Act: -0.1700
Data Index: 6746144 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.0582. Min Act: -0.1700
Data Index: 7584136 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.0269. Min Act: -0.1700
Data Index: 420637 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.0269. Min Act: -0.1700
Data Index: 8023525 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5894. Min Range: -6.5894
Max Act: 6.0269. Min Act: -0.1700
Data Index: 7228073 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9957. Min Act: -0.1700
Data Index: 6160984 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9644. Min Act: -0.1700
Data Index: 2015317 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9644. Min Act: -0.1700
Data Index: 2896971 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6828667 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9332. Min Act: -0.1700
Data Index: 5017697 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7711762 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.8707. Min Act: -0.1700
Data Index: 2493965 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.9019. Min Act: -0.1700
Data Index: 4986972 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.8394. Min Act: -0.1700
Data Index: 6048584 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.8394. Min Act: -0.1700
Data Index: 7950282 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5894. Min Range: -6.5894
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1331811 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19