Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.7221. Min Act: -0.1700
Data Index: 8571667 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.5346. Min Act: -0.1700
Data Index: 1475959 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.3471. Min Act: -0.1700
Data Index: 8260237 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.2534. Min Act: -0.1700
Data Index: 6112107 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.2221. Min Act: -0.1700
Data Index: 634675 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.1596. Min Act: -0.1700
Data Index: 4077708 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.1284. Min Act: -0.1700
Data Index: 5043828 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.0971. Min Act: -0.1700
Data Index: 7352501 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.1284. Min Act: -0.1700
Data Index: 8777706 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7221. Min Range: -7.7221
Max Act: 7.0659. Min Act: -0.1700
Data Index: 3411871 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.9721. Min Act: -0.1700
Data Index: 6535889 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.9409. Min Act: -0.1700
Data Index: 4628621 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.9409. Min Act: -0.1700
Data Index: 3404621 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.9409. Min Act: -0.1700
Data Index: 6073752 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.9096. Min Act: -0.1700
Data Index: 2205811 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.8784. Min Act: -0.1700
Data Index: 5661724 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.9096. Min Act: -0.1700
Data Index: 772367 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.8784. Min Act: -0.1700
Data Index: 468484 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.8784. Min Act: -0.1700
Data Index: 2901050 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7221. Min Range: -7.7221
Max Act: 6.8471. Min Act: -0.1700
Data Index: 2519218 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19