Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4871 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.8377. Min Act: -0.1700
Data Index: 524045 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.6815. Min Act: -0.1700
Data Index: 2949120 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.6190. Min Act: -0.1700
Data Index: 7063076 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.5565. Min Act: -0.1700
Data Index: 8495295 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.5565. Min Act: -0.1700
Data Index: 6215799 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.5252. Min Act: -0.1700
Data Index: 7780396 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4940. Min Act: -0.1700
Data Index: 4084253 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4940. Min Act: -0.1700
Data Index: 6291728 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4627. Min Act: -0.1700
Data Index: 6807304 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4627. Min Act: -0.1700
Data Index: 5836851 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4315. Min Act: -0.1700
Data Index: 5401524 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4315. Min Act: -0.1700
Data Index: 5110897 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4002. Min Act: -0.1700
Data Index: 2243716 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4002. Min Act: -0.1700
Data Index: 4839268 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.4002. Min Act: -0.1700
Data Index: 5165895 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.3377. Min Act: -0.1700
Data Index: 3537378 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.3377. Min Act: -0.1700
Data Index: 3945630 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.3377. Min Act: -0.1700
Data Index: 5120188 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.3377. Min Act: -0.1700
Data Index: 6590835 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8377. Min Range: -6.8377
Max Act: 6.2752. Min Act: -0.1700
Data Index: 4589833 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19