Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5917 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2100. Min Range: -8.2100
Max Act: 8.2100. Min Act: -0.1700
Data Index: 8574324 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.7725. Min Act: -0.1700
Data Index: 2330088 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.6475. Min Act: -0.1700
Data Index: 6339576 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.5850. Min Act: -0.1700
Data Index: 1621368 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.4600. Min Act: -0.1700
Data Index: 3627770 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.3975. Min Act: -0.1700
Data Index: 4650318 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.3975. Min Act: -0.1700
Data Index: 8526706 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.3662. Min Act: -0.1700
Data Index: 4456115 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.3037. Min Act: -0.1700
Data Index: 2406953 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2725. Min Act: -0.1700
Data Index: 8376375 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2725. Min Act: -0.1700
Data Index: 4770831 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2725. Min Act: -0.1700
Data Index: 40275 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2725. Min Act: -0.1700
Data Index: 2671365 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2412. Min Act: -0.1700
Data Index: 3936007 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2725. Min Act: -0.1700
Data Index: 8803188 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2412. Min Act: -0.1700
Data Index: 8808207 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.2100. Min Act: -0.1700
Data Index: 5558216 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.1787. Min Act: -0.1700
Data Index: 1335067 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.1787. Min Act: -0.1700
Data Index: 4049922 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2100. Min Range: -8.2100
Max Act: 7.1475. Min Act: -0.1700
Data Index: 3132612 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19