Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.5643. Min Act: -0.1700
Data Index: 4864955 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.5643. Min Act: -0.1700
Data Index: 4355660 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.5331. Min Act: -0.1700
Data Index: 7964009 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4706. Min Act: -0.1700
Data Index: 65525 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4706. Min Act: -0.1700
Data Index: 6758537 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4706. Min Act: -0.1700
Data Index: 3745720 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4081. Min Act: -0.1700
Data Index: 2856655 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4393. Min Act: -0.1700
Data Index: 2607574 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4393. Min Act: -0.1700
Data Index: 7895900 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4393. Min Act: -0.1700
Data Index: 1568103 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4081. Min Act: -0.1700
Data Index: 4814160 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4081. Min Act: -0.1700
Data Index: 1572138 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4081. Min Act: -0.1700
Data Index: 7959939 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.4081. Min Act: -0.1700
Data Index: 2558603 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.3768. Min Act: -0.1700
Data Index: 7047042 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.3456. Min Act: -0.1700
Data Index: 8824526 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.3456. Min Act: -0.1700
Data Index: 6106256 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.3456. Min Act: -0.1700
Data Index: 4087517 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.3456. Min Act: -0.1700
Data Index: 8467305 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5643. Min Range: -5.5643
Max Act: 5.3143. Min Act: -0.1700
Data Index: 4314040 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19