Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 10 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.2341. Min Act: -0.1700
Data Index: 2962726 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.2165. Min Act: -0.1700
Data Index: 5042376 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.2077. Min Act: -0.1699
Data Index: 7344967 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.2077. Min Act: -0.1693
Data Index: 2239850 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.2077. Min Act: -0.1685
Data Index: 8491490 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.2077. Min Act: -0.1669
Data Index: 4101907 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1989. Min Act: -0.1649
Data Index: 8056363 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1989. Min Act: -0.1700
Data Index: 4920719 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1989. Min Act: -0.1677
Data Index: 6034700 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1989. Min Act: -0.1697
Data Index: 6594257 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1901. Min Act: -0.1666
Data Index: 5695042 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1901. Min Act: -0.1700
Data Index: 1709099 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1989. Min Act: -0.1700
Data Index: 4290064 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1725. Min Act: -0.1700
Data Index: 6199726 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1813. Min Act: -0.1666
Data Index: 1075327 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1901. Min Act: -0.1699
Data Index: 8336519 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1813. Min Act: -0.1694
Data Index: 5201767 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1813. Min Act: -0.1464
Data Index: 1920897 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1725. Min Act: -0.1699
Data Index: 3639662 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2341. Min Range: -1.2341
Max Act: 1.1725. Min Act: -0.1673
Data Index: 5030315 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19