Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.8049. Min Act: -0.1700
Data Index: 8185414 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.7424. Min Act: -0.1700
Data Index: 2359468 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.6174. Min Act: -0.1700
Data Index: 6862759 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.4299. Min Act: -0.1700
Data Index: 4864170 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3987. Min Act: -0.1700
Data Index: 2126014 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.3362. Min Act: -0.1700
Data Index: 2021572 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.2424. Min Act: -0.1700
Data Index: 6862757 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.1799. Min Act: -0.1700
Data Index: 4283123 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.1487. Min Act: -0.1700
Data Index: 943973 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.1174. Min Act: -0.1700
Data Index: 7641527 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0862. Min Act: -0.1700
Data Index: 5547330 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0862. Min Act: -0.1700
Data Index: 7418022 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0862. Min Act: -0.1700
Data Index: 2724730 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.1174. Min Act: -0.1700
Data Index: 6608473 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0862. Min Act: -0.1700
Data Index: 1339255 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0549. Min Act: -0.1700
Data Index: 6875914 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0549. Min Act: -0.1700
Data Index: 8385666 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0549. Min Act: -0.1700
Data Index: 5445462 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0549. Min Act: -0.1700
Data Index: 4430170 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8049. Min Range: -6.8049
Max Act: 6.0549. Min Act: -0.1700
Data Index: 4429664 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19