Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1400. Min Range: -7.1400
Max Act: 7.1400. Min Act: -0.1700
Data Index: 7820755 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1400. Min Range: -7.1400
Max Act: 7.0462. Min Act: -0.1700
Data Index: 1567867 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1400. Min Range: -7.1400
Max Act: 7.0462. Min Act: -0.1700
Data Index: 5547197 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.9837. Min Act: -0.1700
Data Index: 1436843 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.9525. Min Act: -0.1700
Data Index: 8609807 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.8900. Min Act: -0.1700
Data Index: 7640115 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.8900. Min Act: -0.1700
Data Index: 6862672 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.8275. Min Act: -0.1700
Data Index: 1845590 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7962. Min Act: -0.1700
Data Index: 7629003 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7962. Min Act: -0.1700
Data Index: 6663067 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7962. Min Act: -0.1700
Data Index: 1567860 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7650. Min Act: -0.1700
Data Index: 2009439 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7337. Min Act: -0.1700
Data Index: 1976950 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7337. Min Act: -0.1700
Data Index: 7295914 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7650. Min Act: -0.1700
Data Index: 7236285 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7337. Min Act: -0.1700
Data Index: 4325409 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.7025. Min Act: -0.1700
Data Index: 5034039 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.6712. Min Act: -0.1700
Data Index: 7323625 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.6712. Min Act: -0.1700
Data Index: 3520705 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1400. Min Range: -7.1400
Max Act: 6.6712. Min Act: -0.1700
Data Index: 1567862 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19