Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.9644. Min Act: -0.1700
Data Index: 8209381 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.9332. Min Act: -0.1700
Data Index: 54729 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.8394. Min Act: -0.1700
Data Index: 6096387 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.7144. Min Act: -0.1700
Data Index: 310901 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.6832. Min Act: -0.1700
Data Index: 7614464 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.6519. Min Act: -0.1700
Data Index: 6178416 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.6832. Min Act: -0.1700
Data Index: 451623 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5894. Min Act: -0.1700
Data Index: 7649081 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5582. Min Act: -0.1700
Data Index: 4215951 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5582. Min Act: -0.1700
Data Index: 4702151 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5269. Min Act: -0.1700
Data Index: 15542 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5269. Min Act: -0.1700
Data Index: 1112853 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5269. Min Act: -0.1700
Data Index: 1946663 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5269. Min Act: -0.1700
Data Index: 8209376 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5269. Min Act: -0.1700
Data Index: 1455659 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.4957. Min Act: -0.1700
Data Index: 3893999 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.4957. Min Act: -0.1700
Data Index: 3145931 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.5269. Min Act: -0.1700
Data Index: 7427174 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.4957. Min Act: -0.1700
Data Index: 6833577 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9644. Min Range: -6.9644
Max Act: 6.4644. Min Act: -0.1700
Data Index: 3856232 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19