Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.4428. Min Act: -0.1700
Data Index: 7967159 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.2865. Min Act: -0.1700
Data Index: 8282780 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.1928. Min Act: -0.1700
Data Index: 7631894 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.1615. Min Act: -0.1700
Data Index: 438813 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.0990. Min Act: -0.1700
Data Index: 6512567 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.0990. Min Act: -0.1700
Data Index: 7711002 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4428. Min Range: -6.4428
Max Act: 6.0365. Min Act: -0.1700
Data Index: 3285901 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9740. Min Act: -0.1700
Data Index: 799386 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9740. Min Act: -0.1700
Data Index: 7523140 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9740. Min Act: -0.1700
Data Index: 8446137 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9428. Min Act: -0.1700
Data Index: 1629238 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 548145 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 6164219 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9428. Min Act: -0.1700
Data Index: 2858446 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.8803. Min Act: -0.1700
Data Index: 3796468 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 3666569 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7219026 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.8803. Min Act: -0.1700
Data Index: 2715181 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.8803. Min Act: -0.1700
Data Index: 4555392 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4428. Min Range: -6.4428
Max Act: 5.8803. Min Act: -0.1700
Data Index: 7132122 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19