Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0229. Min Range: -3.0229
Max Act: 3.0229. Min Act: -0.1700
Data Index: 1804080 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9755. Min Act: -0.1700
Data Index: 1930040 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.9755. Min Act: -0.1700
Data Index: 1725037 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8963. Min Act: -0.1700
Data Index: 5399207 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8805. Min Act: -0.1700
Data Index: 8650060 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8487. Min Act: -0.1700
Data Index: 3554367 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8646. Min Act: -0.1700
Data Index: 6996761 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8169. Min Act: -0.1700
Data Index: 7082636 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8169. Min Act: -0.1700
Data Index: 2157832 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8169. Min Act: -0.1700
Data Index: 5424822 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8169. Min Act: -0.1700
Data Index: 495054 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8010. Min Act: -0.1700
Data Index: 4730188 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7851. Min Act: -0.1700
Data Index: 3920037 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.8010. Min Act: -0.1700
Data Index: 166163 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7851. Min Act: -0.1700
Data Index: 3331118 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7691. Min Act: -0.1700
Data Index: 3869787 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7532. Min Act: -0.1700
Data Index: 7814348 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7691. Min Act: -0.1700
Data Index: 7335241 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7691. Min Act: -0.1700
Data Index: 3277755 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0229. Min Range: -3.0229
Max Act: 2.7691. Min Act: -0.1700
Data Index: 7446423 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19