Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 935 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.5665. Min Act: -0.1700
Data Index: 3329790 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.4728. Min Act: -0.1700
Data Index: 5106831 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3478. Min Act: -0.1700
Data Index: 7049490 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 3247208 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3478. Min Act: -0.1700
Data Index: 3356389 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3165. Min Act: -0.1700
Data Index: 5642772 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3165. Min Act: -0.1700
Data Index: 4089838 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3478. Min Act: -0.1700
Data Index: 759209 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3165. Min Act: -0.1700
Data Index: 7985909 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 6754893 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 2642316 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 5021484 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 879634 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 3572981 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 3132685 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 2005668 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2540. Min Act: -0.1700
Data Index: 4549722 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.3165. Min Act: -0.1700
Data Index: 3148687 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2852. Min Act: -0.1700
Data Index: 4204382 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5665. Min Range: -4.5665
Max Act: 4.2540. Min Act: -0.1700
Data Index: 1979155 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19