Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6334 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3361. Min Range: -6.3361
Max Act: 6.3361. Min Act: -0.1700
Data Index: 4643294 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3361. Min Range: -6.3361
Max Act: 6.1798. Min Act: -0.1700
Data Index: 481663 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3361. Min Range: -6.3361
Max Act: 6.1486. Min Act: -0.1700
Data Index: 5895337 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3361. Min Range: -6.3361
Max Act: 6.1486. Min Act: -0.1700
Data Index: 4643305 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3361. Min Range: -6.3361
Max Act: 6.0548. Min Act: -0.1700
Data Index: 2792216 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.9611. Min Act: -0.1700
Data Index: 1534478 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.9298. Min Act: -0.1700
Data Index: 7153310 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8673. Min Act: -0.1700
Data Index: 770076 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8673. Min Act: -0.1700
Data Index: 804876 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5497209 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8361. Min Act: -0.1700
Data Index: 5383575 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8361. Min Act: -0.1700
Data Index: 4748190 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8048. Min Act: -0.1700
Data Index: 6392470 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8048. Min Act: -0.1700
Data Index: 4220819 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8048. Min Act: -0.1700
Data Index: 8227929 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.8048. Min Act: -0.1700
Data Index: 6140492 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.7736. Min Act: -0.1700
Data Index: 3169850 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.7423. Min Act: -0.1700
Data Index: 5390764 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.7423. Min Act: -0.1700
Data Index: 6467686 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3361. Min Range: -6.3361
Max Act: 5.7423. Min Act: -0.1700
Data Index: 2800407 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19