Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1341. Min Range: -8.1341
Max Act: 8.1341. Min Act: -0.1700
Data Index: 1284397 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.9466. Min Act: -0.1700
Data Index: 1780846 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.9466. Min Act: -0.1700
Data Index: 8567343 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 7769695 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 5460095 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 8343332 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 3752062 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 679562 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 5476002 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8528. Min Act: -0.1700
Data Index: 6277516 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8841. Min Act: -0.1700
Data Index: 8668926 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8216. Min Act: -0.1700
Data Index: 6311297 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8216. Min Act: -0.1700
Data Index: 2098986 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.8216. Min Act: -0.1700
Data Index: 2198953 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.7591. Min Act: -0.1700
Data Index: 732049 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.7903. Min Act: -0.1700
Data Index: 4779815 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.7591. Min Act: -0.1700
Data Index: 1121454 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.7591. Min Act: -0.1700
Data Index: 6267602 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.6966. Min Act: -0.1700
Data Index: 3608233 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1341. Min Range: -8.1341
Max Act: 7.6966. Min Act: -0.1700
Data Index: 2083474 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19