Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6112 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.5580. Min Act: -0.1700
Data Index: 2708896 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.4955. Min Act: -0.1700
Data Index: 3461466 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.4330. Min Act: -0.1700
Data Index: 7904054 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.4330. Min Act: -0.1700
Data Index: 3529701 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.4017. Min Act: -0.1700
Data Index: 8174209 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.4017. Min Act: -0.1700
Data Index: 1345475 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.4017. Min Act: -0.1700
Data Index: 4473959 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.3392. Min Act: -0.1700
Data Index: 626323 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.3080. Min Act: -0.1700
Data Index: 8091779 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.2767. Min Act: -0.1700
Data Index: 1314530 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.2767. Min Act: -0.1700
Data Index: 8053416 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.2142. Min Act: -0.1700
Data Index: 2179464 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1830. Min Act: -0.1700
Data Index: 8078487 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1830. Min Act: -0.1700
Data Index: 1934585 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 8174216 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 765836 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 1728485 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 3243517 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 1469529 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5580. Min Range: -6.5580
Max Act: 6.1205. Min Act: -0.1700
Data Index: 2191142 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19