Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 711 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.2001. Min Act: -0.1700
Data Index: 7753162 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.2001. Min Act: -0.1700
Data Index: 2706112 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.1376. Min Act: -0.1700
Data Index: 1926248 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.1063. Min Act: -0.1700
Data Index: 6562239 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2001. Min Range: -6.2001
Max Act: 6.0438. Min Act: -0.1700
Data Index: 7132532 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.8876. Min Act: -0.1700
Data Index: 7874729 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.7938. Min Act: -0.1700
Data Index: 2637234 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.7001. Min Act: -0.1700
Data Index: 8381861 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.7001. Min Act: -0.1700
Data Index: 6244284 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6688. Min Act: -0.1700
Data Index: 4906468 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.7001. Min Act: -0.1700
Data Index: 4899393 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6688. Min Act: -0.1700
Data Index: 2874367 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6688. Min Act: -0.1700
Data Index: 3699947 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6376. Min Act: -0.1700
Data Index: 6411446 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6063. Min Act: -0.1700
Data Index: 1484454 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6376. Min Act: -0.1700
Data Index: 5946834 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6376. Min Act: -0.1700
Data Index: 3075080 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6063. Min Act: -0.1700
Data Index: 3610829 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6063. Min Act: -0.1700
Data Index: 2298717 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2001. Min Range: -6.2001
Max Act: 5.6063. Min Act: -0.1700
Data Index: 425220 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19