Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 436 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.1258. Min Act: -0.1700
Data Index: 2743533 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0633. Min Act: -0.1700
Data Index: 1588979 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0633. Min Act: -0.1700
Data Index: 3339031 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0008. Min Act: -0.1700
Data Index: 1724863 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0320. Min Act: -0.1700
Data Index: 7799701 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1258. Min Range: -5.1258
Max Act: 5.0008. Min Act: -0.1700
Data Index: 8337560 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8758. Min Act: -0.1700
Data Index: 7799699 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 7088841 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 8658223 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8133. Min Act: -0.1700
Data Index: 8424429 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8133. Min Act: -0.1700
Data Index: 1728069 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7820. Min Act: -0.1700
Data Index: 7791687 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.8445. Min Act: -0.1700
Data Index: 4750300 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7820. Min Act: -0.1700
Data Index: 5675706 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7820. Min Act: -0.1700
Data Index: 7588536 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7508. Min Act: -0.1700
Data Index: 4051890 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7820. Min Act: -0.1700
Data Index: 4652620 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7820. Min Act: -0.1700
Data Index: 6877086 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7508. Min Act: -0.1700
Data Index: 1297915 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1258. Min Range: -5.1258
Max Act: 4.7508. Min Act: -0.1700
Data Index: 5551871 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19