Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 707 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.6654. Min Act: -0.1700
Data Index: 5462079 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.5715. Min Act: -0.1700
Data Index: 8262441 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.3835. Min Act: -0.1700
Data Index: 2822735 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.4149. Min Act: -0.1700
Data Index: 7641739 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.3522. Min Act: -0.1700
Data Index: 88312 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.3678. Min Act: -0.1700
Data Index: 7721542 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.3051. Min Act: -0.1700
Data Index: 6992378 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.2580. Min Act: -0.1700
Data Index: 3000569 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.2737. Min Act: -0.1700
Data Index: 8055645 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.2423. Min Act: -0.1700
Data Index: 989514 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.2580. Min Act: -0.1700
Data Index: 4865323 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.2580. Min Act: -0.1700
Data Index: 6438017 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1951. Min Act: -0.1700
Data Index: 3102094 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1479. Min Act: -0.1700
Data Index: 4175135 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1951. Min Act: -0.1700
Data Index: 448342 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1951. Min Act: -0.1700
Data Index: 5659771 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1951. Min Act: -0.1700
Data Index: 6478597 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1479. Min Act: -0.1700
Data Index: 8550835 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1479. Min Act: -0.1700
Data Index: 1714215 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6654. Min Range: -3.6654
Max Act: 3.1636. Min Act: -0.1700
Data Index: 5738882 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19