Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 605 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1146. Min Range: -6.1146
Max Act: 6.1146. Min Act: -0.1700
Data Index: 6428283 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.8021. Min Act: -0.1700
Data Index: 6262198 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.7708. Min Act: -0.1700
Data Index: 4045553 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.7396. Min Act: -0.1700
Data Index: 8631345 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.7083. Min Act: -0.1700
Data Index: 3525824 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.7396. Min Act: -0.1700
Data Index: 636299 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.7083. Min Act: -0.1700
Data Index: 8757739 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.6771. Min Act: -0.1700
Data Index: 4192611 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.7083. Min Act: -0.1700
Data Index: 5143576 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5944909 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 2158724 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5767914 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 4328459 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 4124372 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 7461739 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5288072 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5521. Min Act: -0.1700
Data Index: 6311911 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.5208. Min Act: -0.1700
Data Index: 3292677 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.4896. Min Act: -0.1700
Data Index: 2284943 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1146. Min Range: -6.1146
Max Act: 5.4896. Min Act: -0.1700
Data Index: 4328461 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19