Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2271. Min Range: -6.2271
Max Act: 6.2271. Min Act: -0.1700
Data Index: 8284354 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2271. Min Range: -6.2271
Max Act: 6.1646. Min Act: -0.1700
Data Index: 1837423 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2271. Min Range: -6.2271
Max Act: 6.1021. Min Act: -0.1700
Data Index: 4590835 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.9458. Min Act: -0.1700
Data Index: 6232821 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.9458. Min Act: -0.1700
Data Index: 1784993 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.9146. Min Act: -0.1700
Data Index: 61107 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.7896. Min Act: -0.1700
Data Index: 6541882 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.7896. Min Act: -0.1700
Data Index: 1186812 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.7583. Min Act: -0.1700
Data Index: 6244458 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.6646. Min Act: -0.1700
Data Index: 1042440 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.6333. Min Act: -0.1700
Data Index: 3425465 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.6333. Min Act: -0.1700
Data Index: 854379 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.6021. Min Act: -0.1700
Data Index: 6940357 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.6021. Min Act: -0.1700
Data Index: 7581904 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.6021. Min Act: -0.1700
Data Index: 6552112 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.5708. Min Act: -0.1700
Data Index: 5946620 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.5708. Min Act: -0.1700
Data Index: 894842 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.5083. Min Act: -0.1700
Data Index: 2994217 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.5083. Min Act: -0.1700
Data Index: 986112 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2271. Min Range: -6.2271
Max Act: 5.5396. Min Act: -0.1700
Data Index: 5833540 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19