Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.5225. Min Act: -0.1700
Data Index: 5454371 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.4912. Min Act: -0.1700
Data Index: 1797391 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3975. Min Act: -0.1700
Data Index: 3083569 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.4287. Min Act: -0.1700
Data Index: 2388920 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3350. Min Act: -0.1700
Data Index: 8575066 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3350. Min Act: -0.1700
Data Index: 6859973 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1698
Data Index: 639777 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3037. Min Act: -0.1700
Data Index: 1059808 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2725. Min Act: -0.1700
Data Index: 7259636 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1700
Data Index: 5478525 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.3037. Min Act: -0.1700
Data Index: 2427526 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2725. Min Act: -0.1700
Data Index: 5067666 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1700
Data Index: 5263624 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1700
Data Index: 7006218 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1700
Data Index: 8023997 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1700
Data Index: 4827167 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2412. Min Act: -0.1700
Data Index: 7408233 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2100. Min Act: -0.1700
Data Index: 1180080 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2100. Min Act: -0.1700
Data Index: 4756792 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5225. Min Range: -4.5225
Max Act: 4.2100. Min Act: -0.1700
Data Index: 7580738 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19