Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2993 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.9233. Min Act: -0.1700
Data Index: 7482396 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.7358. Min Act: -0.1700
Data Index: 4402327 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.5483. Min Act: -0.1700
Data Index: 4563240 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4858. Min Act: -0.1700
Data Index: 2478981 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4858. Min Act: -0.1700
Data Index: 3592080 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4546. Min Act: -0.1700
Data Index: 4945496 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4233. Min Act: -0.1700
Data Index: 2278767 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4233. Min Act: -0.1700
Data Index: 3497939 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4233. Min Act: -0.1700
Data Index: 420093 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.4233. Min Act: -0.1700
Data Index: 5810928 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3608. Min Act: -0.1700
Data Index: 4915011 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3608. Min Act: -0.1700
Data Index: 7838185 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3608. Min Act: -0.1700
Data Index: 3479527 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3921. Min Act: -0.1700
Data Index: 364136 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3608. Min Act: -0.1700
Data Index: 4711045 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3608. Min Act: -0.1700
Data Index: 2189397 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3296. Min Act: -0.1700
Data Index: 3425039 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3296. Min Act: -0.1700
Data Index: 6733371 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3296. Min Act: -0.1700
Data Index: 2756701 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9233. Min Range: -5.9233
Max Act: 5.3296. Min Act: -0.1700
Data Index: 6362766 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19