Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.5248. Min Act: -0.1700
Data Index: 6928666 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.4623. Min Act: -0.1700
Data Index: 2962153 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.4310. Min Act: -0.1700
Data Index: 295062 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.1810. Min Act: -0.1700
Data Index: 1728299 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.1810. Min Act: -0.1700
Data Index: 5113003 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.1498. Min Act: -0.1700
Data Index: 7399065 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.1185. Min Act: -0.1700
Data Index: 292518 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5248. Min Range: -6.5248
Max Act: 6.0248. Min Act: -0.1700
Data Index: 5411951 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9935. Min Act: -0.1700
Data Index: 6761626 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9623. Min Act: -0.1700
Data Index: 7850528 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9310. Min Act: -0.1700
Data Index: 5608721 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9310. Min Act: -0.1700
Data Index: 1202628 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9310. Min Act: -0.1700
Data Index: 955939 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9310. Min Act: -0.1700
Data Index: 736314 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9310. Min Act: -0.1700
Data Index: 1999589 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.9310. Min Act: -0.1700
Data Index: 7989691 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.8685. Min Act: -0.1700
Data Index: 327596 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.8685. Min Act: -0.1700
Data Index: 3939406 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.8685. Min Act: -0.1700
Data Index: 8027079 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5248. Min Range: -6.5248
Max Act: 5.8373. Min Act: -0.1700
Data Index: 5048512 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19