Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1685. Min Range: -5.1685
Max Act: 5.1685. Min Act: -0.1700
Data Index: 4427992 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1685. Min Range: -5.1685
Max Act: 5.0748. Min Act: -0.1700
Data Index: 2537612 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1685. Min Range: -5.1685
Max Act: 5.0435. Min Act: -0.1700
Data Index: 5232144 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 2537620 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 7361897 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 5034317 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 7841209 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1457826 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 4765389 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9810. Min Act: -0.1700
Data Index: 1794792 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9498. Min Act: -0.1700
Data Index: 2991146 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9498. Min Act: -0.1700
Data Index: 7841207 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.8873. Min Act: -0.1700
Data Index: 5408642 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9185. Min Act: -0.1700
Data Index: 1066784 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9185. Min Act: -0.1700
Data Index: 7451369 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.9185. Min Act: -0.1700
Data Index: 6451992 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.8873. Min Act: -0.1700
Data Index: 4416997 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.8873. Min Act: -0.1700
Data Index: 4192480 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.8873. Min Act: -0.1700
Data Index: 7188085 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1685. Min Range: -5.1685
Max Act: 4.8873. Min Act: -0.1700
Data Index: 6776270 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19