Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.5810. Min Act: -0.1700
Data Index: 8431459 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.5498. Min Act: -0.1700
Data Index: 4805549 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.4560. Min Act: -0.1700
Data Index: 2746652 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.4248. Min Act: -0.1700
Data Index: 1880981 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.3935. Min Act: -0.1700
Data Index: 7873424 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.3935. Min Act: -0.1700
Data Index: 5458693 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.3623. Min Act: -0.1700
Data Index: 8702784 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.3623. Min Act: -0.1700
Data Index: 7922157 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.3310. Min Act: -0.1700
Data Index: 5606823 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.3310. Min Act: -0.1700
Data Index: 8574959 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2998. Min Act: -0.1700
Data Index: 3771255 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2998. Min Act: -0.1700
Data Index: 43170 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2685. Min Act: -0.1700
Data Index: 2580194 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2685. Min Act: -0.1700
Data Index: 985150 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2998. Min Act: -0.1700
Data Index: 8060119 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2998. Min Act: -0.1700
Data Index: 73049 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2685. Min Act: -0.1700
Data Index: 5999208 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2685. Min Act: -0.1700
Data Index: 3805190 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2373. Min Act: -0.1700
Data Index: 239684 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5810. Min Range: -5.5810
Max Act: 5.2373. Min Act: -0.1700
Data Index: 1910037 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19