Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 883 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8299. Min Range: -8.8299
Max Act: 8.8299. Min Act: -0.1700
Data Index: 8209729 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8299. Min Range: -8.8299
Max Act: 8.7049. Min Act: -0.1700
Data Index: 1298173 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8299. Min Range: -8.8299
Max Act: 8.7049. Min Act: -0.1700
Data Index: 1844578 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8299. Min Range: -8.8299
Max Act: 8.5174. Min Act: -0.1700
Data Index: 4013315 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8299. Min Range: -8.8299
Max Act: 8.3299. Min Act: -0.1699
Data Index: 882706 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8299. Min Range: -8.8299
Max Act: 8.0799. Min Act: -0.1700
Data Index: 8628813 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.9549. Min Act: -0.1699
Data Index: 5000089 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.9236. Min Act: -0.1700
Data Index: 2015680 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.9236. Min Act: -0.1700
Data Index: 560229 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.9236. Min Act: -0.1700
Data Index: 5902948 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.7986. Min Act: -0.1699
Data Index: 4005900 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.7986. Min Act: -0.1700
Data Index: 2230555 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.8299. Min Act: -0.1700
Data Index: 4346860 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.7361. Min Act: -0.1700
Data Index: 2655484 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.7361. Min Act: -0.1700
Data Index: 3857448 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.6736. Min Act: -0.1700
Data Index: 705163 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.6736. Min Act: -0.1700
Data Index: 6099708 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.6424. Min Act: -0.1700
Data Index: 1089125 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.6111. Min Act: -0.1700
Data Index: 8631611 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8299. Min Range: -8.8299
Max Act: 7.5486. Min Act: -0.1700
Data Index: 1270026 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19