Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.9225. Min Act: -0.1700
Data Index: 404046 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.6100. Min Act: -0.1700
Data Index: 4173359 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.6100. Min Act: -0.1700
Data Index: 7543249 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.6100. Min Act: -0.1700
Data Index: 2234353 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.4850. Min Act: -0.1700
Data Index: 7934787 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.4538. Min Act: -0.1700
Data Index: 6013255 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.5163. Min Act: -0.1700
Data Index: 5948158 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.4225. Min Act: -0.1700
Data Index: 1900662 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.3913. Min Act: -0.1700
Data Index: 3280909 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.4225. Min Act: -0.1700
Data Index: 3842777 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.4225. Min Act: -0.1700
Data Index: 3590656 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.4225. Min Act: -0.1700
Data Index: 3180568 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.3600. Min Act: -0.1700
Data Index: 883995 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.3600. Min Act: -0.1700
Data Index: 7227084 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.3288. Min Act: -0.1700
Data Index: 8417227 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.2975. Min Act: -0.1700
Data Index: 811041 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.2975. Min Act: -0.1700
Data Index: 8329564 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.2663. Min Act: -0.1700
Data Index: 257112 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.2663. Min Act: -0.1700
Data Index: 4750332 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9225. Min Range: -7.9225
Max Act: 7.2350. Min Act: -0.1700
Data Index: 2890806 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19