Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3142 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.9243. Min Act: -0.1692
Data Index: 3074772 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.9243. Min Act: -0.1700
Data Index: 610082 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.6118. Min Act: -0.1700
Data Index: 1272951 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.2993. Min Act: -0.1699
Data Index: 7185061 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.4556. Min Act: -0.1699
Data Index: 334000 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.5806. Min Act: -0.1700
Data Index: 8424992 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.3306. Min Act: -0.1700
Data Index: 2640123 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.4243. Min Act: -0.1699
Data Index: 2199723 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.3306. Min Act: -0.1700
Data Index: 8531114 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.3931. Min Act: -0.1700
Data Index: 1492 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1431. Min Act: -0.1700
Data Index: 1604566 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1743. Min Act: -0.1700
Data Index: 1873853 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1743. Min Act: -0.1700
Data Index: 6248177 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.2368. Min Act: -0.1700
Data Index: 2170624 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1118. Min Act: -0.1689
Data Index: 5095732 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1431. Min Act: -0.1700
Data Index: 2099103 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9243. Min Range: -7.9243
Max Act: 6.9243. Min Act: -0.1700
Data Index: 8258780 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1431. Min Act: -0.1700
Data Index: 2241864 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9243. Min Range: -7.9243
Max Act: 7.1118. Min Act: -0.1700
Data Index: 3620813 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9243. Min Range: -7.9243
Max Act: 6.9556. Min Act: -0.1700
Data Index: 48008 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19