Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.2810. Min Act: -0.1700
Data Index: 415308 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.1873. Min Act: -0.1700
Data Index: 3318464 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.1873. Min Act: -0.1700
Data Index: 6685980 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.1560. Min Act: -0.1700
Data Index: 8413242 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.1247. Min Act: -0.1700
Data Index: 3354719 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.1247. Min Act: -0.1700
Data Index: 2107410 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.0935. Min Act: -0.1700
Data Index: 630581 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.0622. Min Act: -0.1700
Data Index: 481867 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.0310. Min Act: -0.1700
Data Index: 6500985 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.0310. Min Act: -0.1700
Data Index: 1962168 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.0310. Min Act: -0.1700
Data Index: 2241320 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2810. Min Range: -4.2810
Max Act: 4.0310. Min Act: -0.1700
Data Index: 3171648 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9684. Min Act: -0.1700
Data Index: 5964981 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9997. Min Act: -0.1700
Data Index: 5502905 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9997. Min Act: -0.1700
Data Index: 6632661 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9997. Min Act: -0.1700
Data Index: 5373940 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9997. Min Act: -0.1700
Data Index: 7080015 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9684. Min Act: -0.1700
Data Index: 5390410 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9684. Min Act: -0.1700
Data Index: 1461866 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2810. Min Range: -4.2810
Max Act: 3.9684. Min Act: -0.1700
Data Index: 3031254 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19