Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.7649. Min Act: -0.1700
Data Index: 142911 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.7649. Min Act: -0.1700
Data Index: 1512964 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.7024. Min Act: -0.1700
Data Index: 8097399 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.6399. Min Act: -0.1700
Data Index: 8818660 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.6087. Min Act: -0.1700
Data Index: 3017952 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.5774. Min Act: -0.1700
Data Index: 4787405 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.5774. Min Act: -0.1700
Data Index: 6754375 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.5149. Min Act: -0.1700
Data Index: 7225573 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.4837. Min Act: -0.1700
Data Index: 7655713 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.3899. Min Act: -0.1700
Data Index: 1809424 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.3274. Min Act: -0.1700
Data Index: 6758415 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.2962. Min Act: -0.1700
Data Index: 4851967 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.2024. Min Act: -0.1700
Data Index: 7793537 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.2024. Min Act: -0.1700
Data Index: 852029 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.1712. Min Act: -0.1700
Data Index: 1019341 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.2337. Min Act: -0.1700
Data Index: 2004081 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.1087. Min Act: -0.1700
Data Index: 1618740 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.1399. Min Act: -0.1700
Data Index: 7443357 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.1087. Min Act: -0.1700
Data Index: 177518 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7649. Min Range: -7.7649
Max Act: 7.1087. Min Act: -0.1700
Data Index: 6237933 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19