Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1774. Min Range: -6.1774
Max Act: 6.1774. Min Act: -0.1700
Data Index: 3447383 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1774. Min Range: -6.1774
Max Act: 6.0836. Min Act: -0.1700
Data Index: 5495803 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.9899. Min Act: -0.1700
Data Index: 8025183 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.9586. Min Act: -0.1700
Data Index: 6382100 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1774. Min Range: -6.1774
Max Act: 6.0524. Min Act: -0.1700
Data Index: 2910778 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.9899. Min Act: -0.1700
Data Index: 6355186 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.9586. Min Act: -0.1700
Data Index: 6355185 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.9274. Min Act: -0.1700
Data Index: 1196667 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8649. Min Act: -0.1700
Data Index: 3447382 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8961. Min Act: -0.1700
Data Index: 6382099 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8649. Min Act: -0.1700
Data Index: 5495802 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8336. Min Act: -0.1700
Data Index: 252808 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8649. Min Act: -0.1700
Data Index: 2039537 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8649. Min Act: -0.1700
Data Index: 6355179 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.9274. Min Act: -0.1700
Data Index: 6355184 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8961. Min Act: -0.1700
Data Index: 6355183 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8336. Min Act: -0.1700
Data Index: 7299741 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.7711. Min Act: -0.1700
Data Index: 3876893 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8336. Min Act: -0.1700
Data Index: 5637494 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1774. Min Range: -6.1774
Max Act: 5.8024. Min Act: -0.1700
Data Index: 6361945 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19