Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1802. Min Range: -3.1802
Max Act: 3.1802. Min Act: -0.1700
Data Index: 5435884 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.9752. Min Act: -0.1700
Data Index: 629838 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.9435. Min Act: -0.1700
Data Index: 6018926 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.9277. Min Act: -0.1700
Data Index: 5723281 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.9277. Min Act: -0.1700
Data Index: 3482336 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8801. Min Act: -0.1700
Data Index: 7896604 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8801. Min Act: -0.1700
Data Index: 5494894 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.9118. Min Act: -0.1700
Data Index: 8080544 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8801. Min Act: -0.1700
Data Index: 8814549 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8801. Min Act: -0.1700
Data Index: 1443333 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8642. Min Act: -0.1700
Data Index: 54768 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8642. Min Act: -0.1700
Data Index: 6170116 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8642. Min Act: -0.1700
Data Index: 1919539 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8483. Min Act: -0.1700
Data Index: 137697 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8642. Min Act: -0.1700
Data Index: 4464016 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8324. Min Act: -0.1700
Data Index: 604982 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8324. Min Act: -0.1700
Data Index: 3344656 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8642. Min Act: -0.1700
Data Index: 1198422 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8165. Min Act: -0.1700
Data Index: 6319043 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1802. Min Range: -3.1802
Max Act: 2.8324. Min Act: -0.1700
Data Index: 5870639 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19