Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1610 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2225. Min Range: -8.2225
Max Act: 8.2225. Min Act: -0.1700
Data Index: 4121087 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.9413. Min Act: -0.1700
Data Index: 5786185 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.9100. Min Act: -0.1700
Data Index: 1037521 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.8163. Min Act: -0.1700
Data Index: 7307581 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.6913. Min Act: -0.1700
Data Index: 6950838 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.7538. Min Act: -0.1700
Data Index: 5927077 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.6913. Min Act: -0.1700
Data Index: 4188530 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.6913. Min Act: -0.1700
Data Index: 2912989 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.5663. Min Act: -0.1700
Data Index: 6666118 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.6288. Min Act: -0.1700
Data Index: 5969209 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.3475. Min Act: -0.1700
Data Index: 2265876 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.3788. Min Act: -0.1700
Data Index: 4876964 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.2538. Min Act: -0.1700
Data Index: 4298836 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.2850. Min Act: -0.1700
Data Index: 4000577 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.1913. Min Act: -0.1700
Data Index: 1984338 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.2225. Min Act: -0.1700
Data Index: 508477 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.0663. Min Act: -0.1700
Data Index: 7290967 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2225. Min Range: -8.2225
Max Act: 7.0038. Min Act: -0.1700
Data Index: 5110338 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2225. Min Range: -8.2225
Max Act: 6.9100. Min Act: -0.1700
Data Index: 71560 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2225. Min Range: -8.2225
Max Act: 6.9725. Min Act: -0.1700
Data Index: 5774485 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19