Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1314 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.4850. Min Act: -0.1700
Data Index: 5882010 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.2350. Min Act: -0.1700
Data Index: 1035198 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.1725. Min Act: -0.1700
Data Index: 7649339 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.1725. Min Act: -0.1700
Data Index: 311622 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.1100. Min Act: -0.1700
Data Index: 8358710 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.0788. Min Act: -0.1700
Data Index: 7736217 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.0475. Min Act: -0.1700
Data Index: 5332266 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.0475. Min Act: -0.1700
Data Index: 4664717 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9538. Min Act: -0.1700
Data Index: 4025378 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9538. Min Act: -0.1700
Data Index: 6068523 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9538. Min Act: -0.1700
Data Index: 2636625 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9538. Min Act: -0.1700
Data Index: 7284221 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9850. Min Act: -0.1700
Data Index: 473793 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9225. Min Act: -0.1700
Data Index: 2957706 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9538. Min Act: -0.1700
Data Index: 1047968 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.9538. Min Act: -0.1700
Data Index: 3385794 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.8913. Min Act: -0.1700
Data Index: 6362317 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4850. Min Range: -6.4850
Max Act: 6.0163. Min Act: -0.1700
Data Index: 2713865 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.8913. Min Act: -0.1700
Data Index: 7771307 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4850. Min Range: -6.4850
Max Act: 5.8600. Min Act: -0.1700
Data Index: 235329 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19