Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.6170. Min Act: -0.1700
Data Index: 4325866 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.4920. Min Act: -0.1700
Data Index: 2922084 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.3670. Min Act: -0.1700
Data Index: 2408702 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.3045. Min Act: -0.1700
Data Index: 6057969 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.3045. Min Act: -0.1700
Data Index: 2270476 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.1170. Min Act: -0.1700
Data Index: 701889 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.1170. Min Act: -0.1700
Data Index: 3224805 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.1170. Min Act: -0.1700
Data Index: 3257809 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6170. Min Range: -8.6170
Max Act: 8.0545. Min Act: -0.1700
Data Index: 6293241 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.9920. Min Act: -0.1700
Data Index: 2756255 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.9608. Min Act: -0.1700
Data Index: 2822877 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.9295. Min Act: -0.1700
Data Index: 5277607 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.8670. Min Act: -0.1700
Data Index: 2177288 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.8045. Min Act: -0.1700
Data Index: 5190044 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.8045. Min Act: -0.1700
Data Index: 5151802 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.8045. Min Act: -0.1700
Data Index: 2968794 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.7733. Min Act: -0.1700
Data Index: 6693652 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.7733. Min Act: -0.1700
Data Index: 4478966 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.7733. Min Act: -0.1700
Data Index: 186488 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6170. Min Range: -8.6170
Max Act: 7.7420. Min Act: -0.1700
Data Index: 5497044 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19