Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4356 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6596. Min Range: -6.6596
Max Act: 6.6596. Min Act: -0.1700
Data Index: 5779726 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6596. Min Range: -6.6596
Max Act: 6.2221. Min Act: -0.1700
Data Index: 3460534 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6596. Min Range: -6.6596
Max Act: 6.2221. Min Act: -0.1700
Data Index: 1095475 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6596. Min Range: -6.6596
Max Act: 6.0659. Min Act: -0.1700
Data Index: 7917610 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6596. Min Range: -6.6596
Max Act: 6.0034. Min Act: -0.1700
Data Index: 3328758 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.9096. Min Act: -0.1700
Data Index: 112957 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.8784. Min Act: -0.1700
Data Index: 6155797 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.8471. Min Act: -0.1700
Data Index: 114604 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.8471. Min Act: -0.1700
Data Index: 7417859 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.8159. Min Act: -0.1700
Data Index: 4497942 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.7534. Min Act: -0.1700
Data Index: 4759982 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.7221. Min Act: -0.1700
Data Index: 5836907 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6596. Min Act: -0.1700
Data Index: 7903667 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6909. Min Act: -0.1700
Data Index: 7332461 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6909. Min Act: -0.1700
Data Index: 8663705 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6909. Min Act: -0.1700
Data Index: 929736 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6596. Min Act: -0.1700
Data Index: 3980404 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6284. Min Act: -0.1700
Data Index: 1508883 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6284. Min Act: -0.1700
Data Index: 2316938 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6596. Min Range: -6.6596
Max Act: 5.6284. Min Act: -0.1700
Data Index: 4743233 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19