Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.5360. Min Act: -0.1700
Data Index: 8702933 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.4577. Min Act: -0.1700
Data Index: 323365 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.4420. Min Act: -0.1700
Data Index: 8566054 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.4420. Min Act: -0.1700
Data Index: 2595833 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3950. Min Act: -0.1700
Data Index: 5494537 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.4107. Min Act: -0.1700
Data Index: 7105719 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.4107. Min Act: -0.1700
Data Index: 7548698 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3793. Min Act: -0.1700
Data Index: 1125452 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3323. Min Act: -0.1700
Data Index: 1217042 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3480. Min Act: -0.1700
Data Index: 3825332 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3323. Min Act: -0.1700
Data Index: 1483812 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3480. Min Act: -0.1700
Data Index: 2944982 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3323. Min Act: -0.1700
Data Index: 8606633 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3480. Min Act: -0.1700
Data Index: 3380500 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3323. Min Act: -0.1700
Data Index: 6084468 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3166. Min Act: -0.1700
Data Index: 5752331 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3009. Min Act: -0.1700
Data Index: 4069671 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3166. Min Act: -0.1700
Data Index: 1540473 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.2852. Min Act: -0.1700
Data Index: 7497256 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5360. Min Range: -3.5360
Max Act: 3.3166. Min Act: -0.1700
Data Index: 2688305 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19