Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1302 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.9843. Min Act: -0.1700
Data Index: 8534794 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6135636 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.9843. Min Act: -0.1700
Data Index: 8534793 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.9218. Min Act: -0.1700
Data Index: 7605545 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.8906. Min Act: -0.1700
Data Index: 8058644 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.8593. Min Act: -0.1700
Data Index: 7140695 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.8281. Min Act: -0.1700
Data Index: 2389102 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.8281. Min Act: -0.1700
Data Index: 5512124 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7968. Min Act: -0.1700
Data Index: 2163798 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7656. Min Act: -0.1700
Data Index: 5612014 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7343. Min Act: -0.1700
Data Index: 5188795 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7031. Min Act: -0.1700
Data Index: 6296462 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7343. Min Act: -0.1700
Data Index: 8552614 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7031. Min Act: -0.1700
Data Index: 2077271 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7031. Min Act: -0.1700
Data Index: 8201877 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7031. Min Act: -0.1700
Data Index: 3186134 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7031. Min Act: -0.1700
Data Index: 6335981 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.7031. Min Act: -0.1700
Data Index: 6837638 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.6718. Min Act: -0.1700
Data Index: 805034 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9843. Min Range: -5.9843
Max Act: 5.6718. Min Act: -0.1700
Data Index: 3186957 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19