Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 108 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3889. Min Range: -5.3889
Max Act: 5.3889. Min Act: -0.1700
Data Index: 8047238 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.9201. Min Act: -0.1700
Data Index: 536273 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.8576. Min Act: -0.1700
Data Index: 8340041 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.8889. Min Act: -0.1700
Data Index: 3998142 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7951. Min Act: -0.1700
Data Index: 741239 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7326. Min Act: -0.1700
Data Index: 2993724 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7639. Min Act: -0.1700
Data Index: 2461045 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 1416506 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 3092927 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 8640465 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 3632995 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6701. Min Act: -0.1700
Data Index: 1248316 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 2074571 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.7014. Min Act: -0.1700
Data Index: 2677560 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6701. Min Act: -0.1700
Data Index: 7386058 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6701. Min Act: -0.1700
Data Index: 2694865 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6701. Min Act: -0.1700
Data Index: 1651223 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6701. Min Act: -0.1700
Data Index: 6378207 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6701. Min Act: -0.1700
Data Index: 3768668 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3889. Min Range: -5.3889
Max Act: 4.6389. Min Act: -0.1700
Data Index: 5862034 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19