Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6337 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.7787. Min Act: -0.1700
Data Index: 3687027 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.5912. Min Act: -0.1700
Data Index: 2010532 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.2162. Min Act: -0.1700
Data Index: 8467766 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.2162. Min Act: -0.1700
Data Index: 75669 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.1537. Min Act: -0.1700
Data Index: 5256449 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.1537. Min Act: -0.1700
Data Index: 8446289 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0912. Min Act: -0.1700
Data Index: 1602543 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9662. Min Act: -0.1700
Data Index: 3453627 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0287. Min Act: -0.1700
Data Index: 4160468 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0287. Min Act: -0.1700
Data Index: 4149779 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0287. Min Act: -0.1700
Data Index: 1497308 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0287. Min Act: -0.1700
Data Index: 4551323 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0287. Min Act: -0.1700
Data Index: 7881470 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7787. Min Range: -8.7787
Max Act: 8.0287. Min Act: -0.1700
Data Index: 3026328 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9662. Min Act: -0.1700
Data Index: 2285684 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9662. Min Act: -0.1700
Data Index: 6863250 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9662. Min Act: -0.1700
Data Index: 233879 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9037. Min Act: -0.1700
Data Index: 5144386 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9037. Min Act: -0.1700
Data Index: 7418477 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7787. Min Range: -8.7787
Max Act: 7.9037. Min Act: -0.1700
Data Index: 5617279 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19