Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.7094. Min Act: -0.1700
Data Index: 5402739 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.5219. Min Act: -0.1700
Data Index: 783632 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.4594. Min Act: -0.1700
Data Index: 4432872 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.1782. Min Act: -0.1700
Data Index: 6436901 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.1469. Min Act: -0.1700
Data Index: 2351566 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.1469. Min Act: -0.1700
Data Index: 175424 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.1157. Min Act: -0.1700
Data Index: 412065 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.1469. Min Act: -0.1700
Data Index: 7246748 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.1469. Min Act: -0.1700
Data Index: 222475 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0532. Min Act: -0.1700
Data Index: 126343 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0844. Min Act: -0.1700
Data Index: 1698539 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0532. Min Act: -0.1700
Data Index: 3818249 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0219. Min Act: -0.1700
Data Index: 677871 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0219. Min Act: -0.1700
Data Index: 7962953 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0532. Min Act: -0.1700
Data Index: 7630111 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7094. Min Range: -8.7094
Max Act: 8.0532. Min Act: -0.1700
Data Index: 1264234 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7094. Min Range: -8.7094
Max Act: 7.9907. Min Act: -0.1700
Data Index: 4935293 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7094. Min Range: -8.7094
Max Act: 7.9907. Min Act: -0.1700
Data Index: 4428711 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7094. Min Range: -8.7094
Max Act: 7.9907. Min Act: -0.1700
Data Index: 7462563 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7094. Min Range: -8.7094
Max Act: 7.9907. Min Act: -0.1700
Data Index: 514530 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19