Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1148 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0139. Min Range: -9.0139
Max Act: 9.0139. Min Act: -0.1700
Data Index: 300036 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.8889. Min Act: -0.1700
Data Index: 2075693 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.7014. Min Act: -0.1700
Data Index: 974722 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.6389. Min Act: -0.1700
Data Index: 7688334 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.5764. Min Act: -0.1700
Data Index: 4455140 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.5764. Min Act: -0.1700
Data Index: 3038900 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.5764. Min Act: -0.1700
Data Index: 6871783 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.5139. Min Act: -0.1700
Data Index: 2511859 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.4514. Min Act: -0.1700
Data Index: 6115532 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.2639. Min Act: -0.1700
Data Index: 5992803 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.2014. Min Act: -0.1700
Data Index: 7511780 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.2014. Min Act: -0.1700
Data Index: 2179778 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.1076. Min Act: -0.1700
Data Index: 7641177 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.0764. Min Act: -0.1700
Data Index: 1769491 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.0139. Min Act: -0.1700
Data Index: 5611131 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0139. Min Range: -9.0139
Max Act: 7.9826. Min Act: -0.1700
Data Index: 5600062 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0139. Min Range: -9.0139
Max Act: 8.0139. Min Act: -0.1700
Data Index: 6195049 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0139. Min Range: -9.0139
Max Act: 7.9826. Min Act: -0.1700
Data Index: 5906242 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0139. Min Range: -9.0139
Max Act: 7.9826. Min Act: -0.1700
Data Index: 5538237 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0139. Min Range: -9.0139
Max Act: 7.9514. Min Act: -0.1700
Data Index: 4141254 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19