Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2575 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0113. Min Range: -6.0113
Max Act: 6.0113. Min Act: -0.1700
Data Index: 6299639 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0113. Min Range: -6.0113
Max Act: 6.0113. Min Act: -0.1700
Data Index: 6299650 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.9801. Min Act: -0.1700
Data Index: 6299642 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.9488. Min Act: -0.1700
Data Index: 6299631 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.8551. Min Act: -0.1700
Data Index: 4607454 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.8863. Min Act: -0.1700
Data Index: 4607457 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.7926. Min Act: -0.1700
Data Index: 6152586 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.6363. Min Act: -0.1700
Data Index: 6621604 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.6363. Min Act: -0.1700
Data Index: 8146297 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.5738. Min Act: -0.1700
Data Index: 2139196 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.5426. Min Act: -0.1700
Data Index: 7560073 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.5113. Min Act: -0.1700
Data Index: 7661959 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.5113. Min Act: -0.1700
Data Index: 3720667 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.4801. Min Act: -0.1700
Data Index: 1139836 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.5113. Min Act: -0.1700
Data Index: 8650488 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.5113. Min Act: -0.1700
Data Index: 95187 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.4801. Min Act: -0.1700
Data Index: 6096753 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.4488. Min Act: -0.1700
Data Index: 6916561 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.4176. Min Act: -0.1700
Data Index: 8146296 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0113. Min Range: -6.0113
Max Act: 5.4176. Min Act: -0.1700
Data Index: 6816275 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19