Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.3282. Min Act: -0.1700
Data Index: 4443708 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.2969. Min Act: -0.1700
Data Index: 250761 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.2344. Min Act: -0.1700
Data Index: 8223062 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1719. Min Act: -0.1700
Data Index: 127002 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1719. Min Act: -0.1700
Data Index: 2101045 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1407. Min Act: -0.1700
Data Index: 6244486 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1094. Min Act: -0.1700
Data Index: 6850265 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1094. Min Act: -0.1700
Data Index: 7734243 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.1094. Min Act: -0.1700
Data Index: 4704711 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0782. Min Act: -0.1700
Data Index: 6732896 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0157. Min Act: -0.1700
Data Index: 3865539 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3282. Min Range: -7.3282
Max Act: 7.0157. Min Act: -0.1700
Data Index: 5430359 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9844. Min Act: -0.1700
Data Index: 49883 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9844. Min Act: -0.1700
Data Index: 8078806 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9844. Min Act: -0.1700
Data Index: 549440 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9844. Min Act: -0.1700
Data Index: 5759205 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9844. Min Act: -0.1700
Data Index: 8097066 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9532. Min Act: -0.1700
Data Index: 2700340 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9219. Min Act: -0.1700
Data Index: 6783108 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3282. Min Range: -7.3282
Max Act: 6.9219. Min Act: -0.1700
Data Index: 4804132 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19