Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5856 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.9390. Min Act: -0.1700
Data Index: 5611881 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.8765. Min Act: -0.1700
Data Index: 3634803 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.6890. Min Act: -0.1700
Data Index: 1213571 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.6577. Min Act: -0.1700
Data Index: 7978048 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5952. Min Act: -0.1700
Data Index: 3721249 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5640. Min Act: -0.1700
Data Index: 8489622 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5952. Min Act: -0.1700
Data Index: 5420554 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5640. Min Act: -0.1700
Data Index: 12958 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5640. Min Act: -0.1700
Data Index: 4688065 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5015. Min Act: -0.1700
Data Index: 3176726 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5015. Min Act: -0.1700
Data Index: 5743122 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4702. Min Act: -0.1700
Data Index: 4535122 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4702. Min Act: -0.1700
Data Index: 1851438 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.5015. Min Act: -0.1700
Data Index: 1855582 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4702. Min Act: -0.1700
Data Index: 4620173 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4702. Min Act: -0.1700
Data Index: 304540 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4077. Min Act: -0.1700
Data Index: 7666729 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4390. Min Act: -0.1700
Data Index: 8432724 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4077. Min Act: -0.1700
Data Index: 5929647 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9390. Min Range: -6.9390
Max Act: 6.4077. Min Act: -0.1700
Data Index: 4601944 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19