Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.5287. Min Act: -0.1700
Data Index: 4380979 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.4037. Min Act: -0.1700
Data Index: 3700091 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.3412. Min Act: -0.1700
Data Index: 3192333 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.3412. Min Act: -0.1700
Data Index: 3700090 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.2787. Min Act: -0.1700
Data Index: 6527664 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.2787. Min Act: -0.1700
Data Index: 2992425 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.1537. Min Act: -0.1700
Data Index: 1937493 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.1537. Min Act: -0.1700
Data Index: 517228 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0912. Min Act: -0.1700
Data Index: 4284260 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.1537. Min Act: -0.1700
Data Index: 2677478 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 1819626 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 6673134 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 133919 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 6043779 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 7752450 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 1875902 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5287. Min Range: -8.5287
Max Act: 8.0287. Min Act: -0.1700
Data Index: 453741 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5287. Min Range: -8.5287
Max Act: 7.9662. Min Act: -0.1700
Data Index: 7645625 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5287. Min Range: -8.5287
Max Act: 7.9662. Min Act: -0.1700
Data Index: 5343766 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5287. Min Range: -8.5287
Max Act: 7.9662. Min Act: -0.1700
Data Index: 5620135 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19