Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 659 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1271. Min Range: -7.1271
Max Act: 7.1271. Min Act: -0.1700
Data Index: 6755200 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7834. Min Act: -0.1700
Data Index: 1498227 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7521. Min Act: -0.1700
Data Index: 1678098 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7521. Min Act: -0.1700
Data Index: 2777021 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7209. Min Act: -0.1700
Data Index: 576871 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.6896. Min Act: -0.1700
Data Index: 8046632 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.6896. Min Act: -0.1700
Data Index: 1270076 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.6896. Min Act: -0.1700
Data Index: 4358252 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.7209. Min Act: -0.1700
Data Index: 1223674 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5959. Min Act: -0.1700
Data Index: 5756341 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5959. Min Act: -0.1700
Data Index: 890636 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5646. Min Act: -0.1700
Data Index: 1706063 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5646. Min Act: -0.1700
Data Index: 8781617 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5334. Min Act: -0.1700
Data Index: 7641862 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5334. Min Act: -0.1700
Data Index: 5191812 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5646. Min Act: -0.1700
Data Index: 6495383 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5021. Min Act: -0.1700
Data Index: 6463871 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5021. Min Act: -0.1700
Data Index: 3191162 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5021. Min Act: -0.1700
Data Index: 1048660 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1271. Min Range: -7.1271
Max Act: 6.5021. Min Act: -0.1700
Data Index: 2382109 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19