Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1003. Min Range: -6.1003
Max Act: 6.1003. Min Act: -0.1700
Data Index: 7468362 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.6628. Min Act: -0.1700
Data Index: 2368473 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.6003. Min Act: -0.1700
Data Index: 7572298 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.6003. Min Act: -0.1700
Data Index: 1907415 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.5690. Min Act: -0.1700
Data Index: 2811803 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.5378. Min Act: -0.1700
Data Index: 53167 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.5690. Min Act: -0.1700
Data Index: 3653260 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.5065. Min Act: -0.1700
Data Index: 8012795 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6031842 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.4753. Min Act: -0.1700
Data Index: 3509189 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.4440. Min Act: -0.1700
Data Index: 6140970 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.4128. Min Act: -0.1700
Data Index: 5974251 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.4128. Min Act: -0.1700
Data Index: 4338851 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3815. Min Act: -0.1700
Data Index: 6145358 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3503. Min Act: -0.1700
Data Index: 8476347 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3503. Min Act: -0.1700
Data Index: 7641437 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3190. Min Act: -0.1700
Data Index: 1090901 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3190. Min Act: -0.1700
Data Index: 4709740 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3190. Min Act: -0.1700
Data Index: 4657761 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1003. Min Range: -6.1003
Max Act: 5.3190. Min Act: -0.1700
Data Index: 3085442 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19