Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.6078. Min Act: -0.1700
Data Index: 8571960 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.5141. Min Act: -0.1700
Data Index: 140909 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.3578. Min Act: -0.1700
Data Index: 755299 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.3578. Min Act: -0.1700
Data Index: 6773274 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.3266. Min Act: -0.1700
Data Index: 8425498 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.2641. Min Act: -0.1700
Data Index: 4161398 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.2641. Min Act: -0.1700
Data Index: 2249780 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.2328. Min Act: -0.1700
Data Index: 7204378 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.2016. Min Act: -0.1700
Data Index: 6555458 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.2016. Min Act: -0.1700
Data Index: 837924 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1703. Min Act: -0.1700
Data Index: 4972164 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 8035735 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1703. Min Act: -0.1700
Data Index: 5493645 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 982467 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 1066705 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 4137638 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 6516396 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 2964052 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1391. Min Act: -0.1700
Data Index: 8725865 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6078. Min Range: -5.6078
Max Act: 5.1078. Min Act: -0.1700
Data Index: 7604658 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19