Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.9931. Min Act: -0.1700
Data Index: 3346172 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.7744. Min Act: -0.1700
Data Index: 981356 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.7119. Min Act: -0.1700
Data Index: 4585822 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.6806. Min Act: -0.1700
Data Index: 2504480 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.6806. Min Act: -0.1700
Data Index: 7461369 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.6181. Min Act: -0.1700
Data Index: 8003952 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.5869. Min Act: -0.1700
Data Index: 4196095 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.6181. Min Act: -0.1700
Data Index: 389746 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.5869. Min Act: -0.1700
Data Index: 3395117 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.6181. Min Act: -0.1700
Data Index: 69333 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.5244. Min Act: -0.1700
Data Index: 7150629 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.5556. Min Act: -0.1700
Data Index: 8306628 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.5244. Min Act: -0.1700
Data Index: 437992 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.4931. Min Act: -0.1700
Data Index: 2335283 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.4306. Min Act: -0.1700
Data Index: 1349763 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.4306. Min Act: -0.1700
Data Index: 6086068 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.3994. Min Act: -0.1700
Data Index: 2132936 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.3681. Min Act: -0.1700
Data Index: 2623708 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.3994. Min Act: -0.1700
Data Index: 799213 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9931. Min Range: -6.9931
Max Act: 6.3056. Min Act: -0.1700
Data Index: 1901898 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19