Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1763 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.9883. Min Act: -0.1700
Data Index: 5004421 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.6758. Min Act: -0.1700
Data Index: 3710145 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.6133. Min Act: -0.1700
Data Index: 2051710 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.4258. Min Act: -0.1700
Data Index: 6653379 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.5508. Min Act: -0.1700
Data Index: 3086816 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.4883. Min Act: -0.1700
Data Index: 7010253 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.4258. Min Act: -0.1700
Data Index: 6688427 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.4258. Min Act: -0.1700
Data Index: 2051708 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3633. Min Act: -0.1700
Data Index: 720302 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3633. Min Act: -0.1700
Data Index: 3283925 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3633. Min Act: -0.1700
Data Index: 2901030 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3633. Min Act: -0.1700
Data Index: 5028436 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.4258. Min Act: -0.1700
Data Index: 1802011 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3008. Min Act: -0.1700
Data Index: 2582660 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3008. Min Act: -0.1700
Data Index: 4334555 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.1758. Min Act: -0.1700
Data Index: 1830627 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.3008. Min Act: -0.1700
Data Index: 4463951 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.2071. Min Act: -0.1700
Data Index: 6510123 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.2383. Min Act: -0.1700
Data Index: 3359703 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9883. Min Range: -8.9883
Max Act: 8.1758. Min Act: -0.1700
Data Index: 1439464 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19