Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 795 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.4766. Min Act: -0.1700
Data Index: 3697601 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.4141. Min Act: -0.1700
Data Index: 3317412 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.2891. Min Act: -0.1700
Data Index: 7451782 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.2266. Min Act: -0.1700
Data Index: 3394865 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.2266. Min Act: -0.1700
Data Index: 3130084 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.2266. Min Act: -0.1700
Data Index: 4536018 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.2266. Min Act: -0.1700
Data Index: 1849284 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1953. Min Act: -0.1700
Data Index: 1417495 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1953. Min Act: -0.1700
Data Index: 7170543 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1641. Min Act: -0.1700
Data Index: 6748518 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1641. Min Act: -0.1700
Data Index: 7919716 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1976998 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1641. Min Act: -0.1700
Data Index: 4922652 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1016. Min Act: -0.1700
Data Index: 2542859 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1328. Min Act: -0.1700
Data Index: 7388309 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1328. Min Act: -0.1700
Data Index: 1007079 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1016. Min Act: -0.1700
Data Index: 2808632 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1016. Min Act: -0.1700
Data Index: 6553819 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.1016. Min Act: -0.1700
Data Index: 1027446 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4766. Min Range: -6.4766
Max Act: 6.0703. Min Act: -0.1700
Data Index: 7347854 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19