Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0327. Min Act: -0.1700
Data Index: 5861764 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0327. Min Range: -5.0327
Max Act: 5.0014. Min Act: -0.1700
Data Index: 5743087 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8452. Min Act: -0.1700
Data Index: 6874582 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.8139. Min Act: -0.1700
Data Index: 8452427 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7827. Min Act: -0.1700
Data Index: 8701346 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7827. Min Act: -0.1700
Data Index: 8099180 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7514. Min Act: -0.1700
Data Index: 1172761 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6889. Min Act: -0.1700
Data Index: 5057897 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7202. Min Act: -0.1700
Data Index: 6985346 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.7202. Min Act: -0.1700
Data Index: 7461311 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6889. Min Act: -0.1700
Data Index: 5212990 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6889. Min Act: -0.1700
Data Index: 7925468 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6889. Min Act: -0.1700
Data Index: 4526944 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6577. Min Act: -0.1700
Data Index: 4326546 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6889. Min Act: -0.1700
Data Index: 5278238 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6577. Min Act: -0.1700
Data Index: 5916769 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6264. Min Act: -0.1700
Data Index: 1333276 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6264. Min Act: -0.1700
Data Index: 3202980 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6264. Min Act: -0.1700
Data Index: 525053 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0327. Min Range: -5.0327
Max Act: 4.6264. Min Act: -0.1700
Data Index: 5716528 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19