Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 127 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4409. Min Range: -9.4409
Max Act: 9.4409. Min Act: -0.1700
Data Index: 3643921 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.6284. Min Act: -0.1700
Data Index: 6891238 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.6284. Min Act: -0.1700
Data Index: 5699146 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.4409. Min Act: -0.1700
Data Index: 3133969 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.3784. Min Act: -0.1700
Data Index: 1491832 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.3784. Min Act: -0.1700
Data Index: 8056565 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.3159. Min Act: -0.1700
Data Index: 3550931 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.3159. Min Act: -0.1700
Data Index: 1003542 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.2534. Min Act: -0.1700
Data Index: 7329671 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.1909. Min Act: -0.1700
Data Index: 5391951 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.1909. Min Act: -0.1700
Data Index: 3797785 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.1284. Min Act: -0.1700
Data Index: 2570785 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0659. Min Act: -0.1700
Data Index: 6477069 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0659. Min Act: -0.1700
Data Index: 6955639 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0034. Min Act: -0.1700
Data Index: 3647981 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0034. Min Act: -0.1700
Data Index: 4694474 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0034. Min Act: -0.1700
Data Index: 5825497 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0034. Min Act: -0.1700
Data Index: 7583846 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4409. Min Range: -9.4409
Max Act: 8.0034. Min Act: -0.1700
Data Index: 1007320 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4409. Min Range: -9.4409
Max Act: 7.9409. Min Act: -0.1700
Data Index: 6144151 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19