Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.3526. Min Act: -0.1700
Data Index: 2086516 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.2901. Min Act: -0.1700
Data Index: 203147 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 4222963 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 5459680 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 8703900 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.2276. Min Act: -0.1700
Data Index: 266465 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.1651. Min Act: -0.1700
Data Index: 5646709 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.0401. Min Act: -0.1700
Data Index: 6867222 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.0401. Min Act: -0.1700
Data Index: 6371223 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.0401. Min Act: -0.1700
Data Index: 2926474 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.0401. Min Act: -0.1700
Data Index: 4944400 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3526. Min Range: -8.3526
Max Act: 8.0401. Min Act: -0.1700
Data Index: 5813472 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9776. Min Act: -0.1700
Data Index: 2509791 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9776. Min Act: -0.1700
Data Index: 6326940 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9776. Min Act: -0.1700
Data Index: 8314314 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9776. Min Act: -0.1700
Data Index: 3057341 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9776. Min Act: -0.1700
Data Index: 8693571 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9151. Min Act: -0.1700
Data Index: 3917223 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9151. Min Act: -0.1700
Data Index: 4020587 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3526. Min Range: -8.3526
Max Act: 7.9151. Min Act: -0.1700
Data Index: 970451 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19