Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.4389. Min Act: -0.1700
Data Index: 3790467 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.2827. Min Act: -0.1700
Data Index: 1876048 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.1889. Min Act: -0.1700
Data Index: 3327595 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.0639. Min Act: -0.1700
Data Index: 2854262 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.0639. Min Act: -0.1700
Data Index: 934174 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.0014. Min Act: -0.1700
Data Index: 8115107 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4389. Min Range: -6.4389
Max Act: 6.0014. Min Act: -0.1700
Data Index: 1416352 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.9702. Min Act: -0.1700
Data Index: 1416353 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.9389. Min Act: -0.1700
Data Index: 6859253 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.9077. Min Act: -0.1700
Data Index: 7952318 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.9389. Min Act: -0.1700
Data Index: 4745552 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.9389. Min Act: -0.1700
Data Index: 7314130 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.9077. Min Act: -0.1700
Data Index: 6777689 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.8764. Min Act: -0.1700
Data Index: 1195306 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.8764. Min Act: -0.1700
Data Index: 1050165 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.8452. Min Act: -0.1700
Data Index: 3456561 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.8139. Min Act: -0.1700
Data Index: 4489234 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.8452. Min Act: -0.1700
Data Index: 4401454 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.7827. Min Act: -0.1700
Data Index: 6352022 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4389. Min Range: -6.4389
Max Act: 5.8139. Min Act: -0.1700
Data Index: 3251985 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19