Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3149 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4245. Min Range: -6.4245
Max Act: 6.4245. Min Act: -0.1700
Data Index: 828332 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4245. Min Range: -6.4245
Max Act: 6.4245. Min Act: -0.1700
Data Index: 6602433 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4245. Min Range: -6.4245
Max Act: 6.1432. Min Act: -0.1700
Data Index: 1938863 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4245. Min Range: -6.4245
Max Act: 6.1120. Min Act: -0.1700
Data Index: 4929630 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4245. Min Range: -6.4245
Max Act: 6.0182. Min Act: -0.1700
Data Index: 194911 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9870. Min Act: -0.1700
Data Index: 6575554 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9557. Min Act: -0.1700
Data Index: 3334605 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9557. Min Act: -0.1700
Data Index: 3897284 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9245. Min Act: -0.1700
Data Index: 3185984 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9245. Min Act: -0.1700
Data Index: 1984267 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9245. Min Act: -0.1700
Data Index: 5838545 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4430757 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8932. Min Act: -0.1700
Data Index: 6726724 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4314376 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8932. Min Act: -0.1700
Data Index: 5272525 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8932. Min Act: -0.1700
Data Index: 1291208 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8932. Min Act: -0.1700
Data Index: 6419874 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 3380579 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 4557787 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4245. Min Range: -6.4245
Max Act: 5.8620. Min Act: -0.1700
Data Index: 4815860 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19