Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4404 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3099. Min Range: -5.3099
Max Act: 5.3099. Min Act: -0.1700
Data Index: 4400692 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3099. Min Range: -5.3099
Max Act: 5.1536. Min Act: -0.1700
Data Index: 4675445 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3099. Min Range: -5.3099
Max Act: 5.0911. Min Act: -0.1700
Data Index: 3667834 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3099. Min Range: -5.3099
Max Act: 5.0286. Min Act: -0.1700
Data Index: 1915581 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.9661. Min Act: -0.1700
Data Index: 7362641 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.9036. Min Act: -0.1700
Data Index: 3000371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.9661. Min Act: -0.1700
Data Index: 3385535 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.9036. Min Act: -0.1700
Data Index: 6425315 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.9036. Min Act: -0.1700
Data Index: 6123493 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.9036. Min Act: -0.1700
Data Index: 6492876 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.8724. Min Act: -0.1700
Data Index: 2638291 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.8411. Min Act: -0.1700
Data Index: 5121015 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.8411. Min Act: -0.1700
Data Index: 6017075 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.8099. Min Act: -0.1700
Data Index: 4109693 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.7786. Min Act: -0.1700
Data Index: 4587243 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.7786. Min Act: -0.1700
Data Index: 78143 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.8099. Min Act: -0.1700
Data Index: 669664 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.7786. Min Act: -0.1700
Data Index: 7721228 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.7786. Min Act: -0.1700
Data Index: 4705937 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3099. Min Range: -5.3099
Max Act: 4.7161. Min Act: -0.1700
Data Index: 3206050 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19