Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1668 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0168. Min Range: -5.0168
Max Act: 5.0168. Min Act: -0.1700
Data Index: 7069536 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9856. Min Act: -0.1700
Data Index: 60926 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9543. Min Act: -0.1700
Data Index: 7068400 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9543. Min Act: -0.1700
Data Index: 8687407 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9543. Min Act: -0.1700
Data Index: 1912250 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9543. Min Act: -0.1700
Data Index: 6920923 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9231. Min Act: -0.1700
Data Index: 5553152 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.9231. Min Act: -0.1700
Data Index: 963987 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8918. Min Act: -0.1700
Data Index: 2499336 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8606. Min Act: -0.1700
Data Index: 8693812 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8606. Min Act: -0.1700
Data Index: 1748772 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8606. Min Act: -0.1700
Data Index: 499312 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8606. Min Act: -0.1700
Data Index: 768271 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8293. Min Act: -0.1700
Data Index: 4088797 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8293. Min Act: -0.1700
Data Index: 4790905 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.8293. Min Act: -0.1700
Data Index: 3645198 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.7981. Min Act: -0.1700
Data Index: 4993962 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.7668. Min Act: -0.1700
Data Index: 3737643 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.7668. Min Act: -0.1700
Data Index: 30100 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0168. Min Range: -5.0168
Max Act: 4.7668. Min Act: -0.1700
Data Index: 6553839 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19