Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.3284. Min Act: -0.1700
Data Index: 1058259 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2813. Min Act: -0.1700
Data Index: 8098776 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2656. Min Act: -0.1700
Data Index: 223424 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2656. Min Act: -0.1700
Data Index: 1796823 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2499. Min Act: -0.1700
Data Index: 6706352 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2499. Min Act: -0.1700
Data Index: 6939628 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2499. Min Act: -0.1700
Data Index: 7560955 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 3690176 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 3001631 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 3048579 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 3982354 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 8831837 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 4004737 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 963892 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 2835950 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 1711988 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2184. Min Act: -0.1700
Data Index: 8074028 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2341. Min Act: -0.1700
Data Index: 6454830 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2184. Min Act: -0.1700
Data Index: 8695435 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3284. Min Range: -3.3284
Max Act: 3.2184. Min Act: -0.1700
Data Index: 1972728 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19