Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 10.3011. Min Range: -10.3011
Max Act: 9.9886. Min Act: -0.1700
Data Index: 402634 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3011. Min Range: -10.3011
Max Act: 10.3011. Min Act: -0.1700
Data Index: 3903788 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3011. Min Range: -10.3011
Max Act: 8.5511. Min Act: -0.1700
Data Index: 3594192 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3011. Min Range: -10.3011
Max Act: 7.9886. Min Act: -0.1700
Data Index: 5143033 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3011. Min Range: -10.3011
Max Act: 8.2386. Min Act: -0.1700
Data Index: 2889493 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3011. Min Range: -10.3011
Max Act: 6.3949. Min Act: -0.1700
Data Index: 3530753 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3011. Min Range: -10.3011
Max Act: 7.5824. Min Act: -0.1700
Data Index: 3903789 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3011. Min Range: -10.3011
Max Act: 5.0199. Min Act: 0.0483
Data Index: 447816 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3011. Min Range: -10.3011
Max Act: 8.3011. Min Act: -0.1700
Data Index: 4008096 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3011. Min Range: -10.3011
Max Act: 6.3949. Min Act: -0.1700
Data Index: 8501195 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3011. Min Range: -10.3011
Max Act: 6.6449. Min Act: -0.1700
Data Index: 7640518 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3011. Min Range: -10.3011
Max Act: 5.2699. Min Act: -0.1700
Data Index: 8544795 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3011. Min Range: -10.3011
Max Act: 7.8636. Min Act: -0.1700
Data Index: 8680348 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3011. Min Range: -10.3011
Max Act: 8.0511. Min Act: -0.1700
Data Index: 3459287 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3011. Min Range: -10.3011
Max Act: 5.5199. Min Act: -0.1700
Data Index: 2901629 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3011. Min Range: -10.3011
Max Act: 7.8636. Min Act: -0.1700
Data Index: 2803877 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3011. Min Range: -10.3011
Max Act: 6.7699. Min Act: -0.1700
Data Index: 3877178 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3011. Min Range: -10.3011
Max Act: 6.3636. Min Act: -0.1700
Data Index: 5091468 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3011. Min Range: -10.3011
Max Act: 7.5511. Min Act: -0.1700
Data Index: 4095053 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3011. Min Range: -10.3011
Max Act: 7.5199. Min Act: -0.1700
Data Index: 628552 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19