Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1372 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.5014. Min Act: -0.1700
Data Index: 955382 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.4077. Min Act: -0.1700
Data Index: 1956583 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.3139. Min Act: -0.1700
Data Index: 3832207 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.3452. Min Act: -0.1700
Data Index: 8040586 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.2514. Min Act: -0.1700
Data Index: 309680 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.2827. Min Act: -0.1700
Data Index: 7413659 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.3139. Min Act: -0.1700
Data Index: 821689 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.2514. Min Act: -0.1700
Data Index: 7381604 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.1577. Min Act: -0.1700
Data Index: 4439998 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.0952. Min Act: -0.1700
Data Index: 4570644 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.0327. Min Act: -0.1700
Data Index: 8022227 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.0014. Min Act: -0.1700
Data Index: 3547308 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.9702. Min Act: -0.1700
Data Index: 3320325 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5014. Min Range: -7.5014
Max Act: 7.0014. Min Act: -0.1700
Data Index: 5058232 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.9702. Min Act: -0.1700
Data Index: 3272941 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.9389. Min Act: -0.1700
Data Index: 8039816 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.9389. Min Act: -0.1700
Data Index: 2287178 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.9389. Min Act: -0.1700
Data Index: 5394663 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.8764. Min Act: -0.1700
Data Index: 3376560 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5014. Min Range: -7.5014
Max Act: 6.9077. Min Act: -0.1700
Data Index: 1177584 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19