Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8317. Min Range: -9.8317
Max Act: 9.8317. Min Act: -0.1700
Data Index: 5660512 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8317. Min Range: -9.8317
Max Act: 9.0192. Min Act: -0.1700
Data Index: 7727059 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8317. Min Range: -9.8317
Max Act: 9.0192. Min Act: -0.1700
Data Index: 4553574 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.8317. Min Act: -0.1700
Data Index: 5284654 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.7067. Min Act: -0.1700
Data Index: 8271132 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.7067. Min Act: -0.1700
Data Index: 5483611 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.7067. Min Act: -0.1700
Data Index: 1757882 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.6442. Min Act: -0.1700
Data Index: 2951907 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.6442. Min Act: -0.1700
Data Index: 8612490 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5817. Min Act: -0.1700
Data Index: 8828530 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5192. Min Act: -0.1700
Data Index: 4222462 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5192. Min Act: -0.1700
Data Index: 2114952 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5192. Min Act: -0.1700
Data Index: 4953954 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5192. Min Act: -0.1700
Data Index: 277961 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5192. Min Act: -0.1700
Data Index: 7904 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.5192. Min Act: -0.1700
Data Index: 8089736 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.3942. Min Act: -0.1700
Data Index: 2226497 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.3942. Min Act: -0.1700
Data Index: 1807045 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.3942. Min Act: -0.1700
Data Index: 3573884 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8317. Min Range: -9.8317
Max Act: 8.3942. Min Act: -0.1700
Data Index: 7958931 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19