Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9810. Min Range: -9.9810
Max Act: 9.9810. Min Act: -0.1700
Data Index: 135133 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9810. Min Range: -9.9810
Max Act: 9.1685. Min Act: -0.1700
Data Index: 2852573 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9810. Min Range: -9.9810
Max Act: 9.0435. Min Act: -0.1700
Data Index: 3336785 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.9185. Min Act: -0.1700
Data Index: 5005772 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.9185. Min Act: -0.1700
Data Index: 6773988 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.9185. Min Act: -0.1700
Data Index: 8235889 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.8560. Min Act: -0.1700
Data Index: 2397179 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 2741968 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.8560. Min Act: -0.1700
Data Index: 3068491 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.9185. Min Act: -0.1700
Data Index: 37163 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.8560. Min Act: -0.1700
Data Index: 2286968 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 6853482 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 7030644 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 4381173 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 4203870 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7310. Min Act: -0.1700
Data Index: 2771938 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7310. Min Act: -0.1700
Data Index: 5493499 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7310. Min Act: -0.1700
Data Index: 3979428 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7935. Min Act: -0.1700
Data Index: 6196895 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9810. Min Range: -9.9810
Max Act: 8.7310. Min Act: -0.1700
Data Index: 674534 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19