Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.4502. Min Act: -0.1700
Data Index: 2708950 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.4190. Min Act: -0.1700
Data Index: 564151 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.3877. Min Act: -0.1700
Data Index: 745350 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.3565. Min Act: -0.1700
Data Index: 8439536 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.3252. Min Act: -0.1700
Data Index: 4184753 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.3565. Min Act: -0.1700
Data Index: 562893 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.3252. Min Act: -0.1700
Data Index: 5134226 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2940. Min Act: -0.1700
Data Index: 6129686 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.3252. Min Act: -0.1700
Data Index: 1111115 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2627. Min Act: -0.1700
Data Index: 2569692 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2315. Min Act: -0.1700
Data Index: 4186020 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2627. Min Act: -0.1700
Data Index: 8484183 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2315. Min Act: -0.1700
Data Index: 2971008 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2315. Min Act: -0.1700
Data Index: 1111116 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2315. Min Act: -0.1700
Data Index: 7209861 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2002. Min Act: -0.1700
Data Index: 8507417 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2002. Min Act: -0.1700
Data Index: 8081414 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2002. Min Act: -0.1700
Data Index: 4406394 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.2002. Min Act: -0.1700
Data Index: 1675394 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4502. Min Range: -5.4502
Max Act: 5.1377. Min Act: -0.1700
Data Index: 3308252 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19