Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1007 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.5350. Min Act: -0.1700
Data Index: 4654801 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.4100. Min Act: -0.1700
Data Index: 8616601 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.4100. Min Act: -0.1700
Data Index: 4640051 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.4100. Min Act: -0.1700
Data Index: 828876 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.4100. Min Act: -0.1700
Data Index: 813159 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3475. Min Act: -0.1700
Data Index: 1661072 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3475. Min Act: -0.1700
Data Index: 5103314 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3163. Min Act: -0.1700
Data Index: 4640050 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3163. Min Act: -0.1700
Data Index: 8616600 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3163. Min Act: -0.1700
Data Index: 7098207 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3163. Min Act: -0.1700
Data Index: 813160 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.3163. Min Act: -0.1700
Data Index: 7987857 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.2225. Min Act: -0.1700
Data Index: 2195239 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.2538. Min Act: -0.1700
Data Index: 1182500 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.1913. Min Act: -0.1700
Data Index: 6670703 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.1600. Min Act: -0.1700
Data Index: 965770 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.1913. Min Act: -0.1700
Data Index: 592021 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.1600. Min Act: -0.1700
Data Index: 7607792 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.1600. Min Act: -0.1700
Data Index: 534332 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5350. Min Range: -8.5350
Max Act: 8.0663. Min Act: -0.1700
Data Index: 6354353 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19