Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4563 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.2583. Min Act: -0.1700
Data Index: 5682899 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5682898 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0708. Min Act: -0.1700
Data Index: 5096519 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 4358881 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0708. Min Act: -0.1700
Data Index: 3443125 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0708. Min Act: -0.1700
Data Index: 1937522 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.1020. Min Act: -0.1700
Data Index: 8026793 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0708. Min Act: -0.1700
Data Index: 7668521 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 5974340 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.1020. Min Act: -0.1700
Data Index: 1763986 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 2944879 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 7283458 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 5252088 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 4053108 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 8424596 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0708. Min Act: -0.1700
Data Index: 5652577 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.9770. Min Act: -0.1700
Data Index: 5949135 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0083. Min Act: -0.1700
Data Index: 6138098 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0083. Min Act: -0.1700
Data Index: 5668281 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0083. Min Act: -0.1700
Data Index: 3667542 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19