Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.8775. Min Act: -0.1700
Data Index: 97360 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.8462. Min Act: -0.1700
Data Index: 6690998 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.8150. Min Act: -0.1700
Data Index: 5716057 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 324076 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.8150. Min Act: -0.1700
Data Index: 6359294 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.8150. Min Act: -0.1700
Data Index: 6750566 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.8150. Min Act: -0.1700
Data Index: 2986827 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 7452002 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7525. Min Act: -0.1700
Data Index: 1500175 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 4963400 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 570229 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 4532183 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 3075845 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7212. Min Act: -0.1700
Data Index: 1839983 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7525. Min Act: -0.1700
Data Index: 883083 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7837. Min Act: -0.1700
Data Index: 6821259 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7212. Min Act: -0.1700
Data Index: 1660848 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.7525. Min Act: -0.1700
Data Index: 2566530 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.6900. Min Act: -0.1700
Data Index: 3772272 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8775. Min Range: -5.8775
Max Act: 5.6900. Min Act: -0.1700
Data Index: 6669150 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19