Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5829 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.4581. Min Act: -0.1700
Data Index: 25092 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.4581. Min Act: -0.1700
Data Index: 7265434 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.3956. Min Act: -0.1700
Data Index: 6987390 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.3956. Min Act: -0.1700
Data Index: 3137917 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.3018. Min Act: -0.1700
Data Index: 7502985 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.2706. Min Act: -0.1700
Data Index: 1867713 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.2393. Min Act: -0.1700
Data Index: 1171949 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.2393. Min Act: -0.1700
Data Index: 6497212 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.2081. Min Act: -0.1700
Data Index: 36498 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.1768. Min Act: -0.1700
Data Index: 3566933 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.1768. Min Act: -0.1700
Data Index: 4545123 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.1456. Min Act: -0.1700
Data Index: 1646841 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.1456. Min Act: -0.1700
Data Index: 1649781 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.1143. Min Act: -0.1700
Data Index: 7393554 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.0831. Min Act: -0.1700
Data Index: 98979 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.0831. Min Act: -0.1700
Data Index: 1893441 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.0831. Min Act: -0.1700
Data Index: 3137918 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.0831. Min Act: -0.1700
Data Index: 586905 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.0831. Min Act: -0.1700
Data Index: 7284825 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4581. Min Range: -6.4581
Max Act: 6.0518. Min Act: -0.1700
Data Index: 4654770 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19