Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.6823. Min Act: -0.1700
Data Index: 8382020 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.6198. Min Act: -0.1700
Data Index: 4591303 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.5573. Min Act: -0.1700
Data Index: 4480802 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.4948. Min Act: -0.1700
Data Index: 3229057 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.4323. Min Act: -0.1700
Data Index: 2348002 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.4323. Min Act: -0.1700
Data Index: 4663430 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.3073. Min Act: -0.1700
Data Index: 5215850 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.3698. Min Act: -0.1700
Data Index: 7779552 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.3073. Min Act: -0.1700
Data Index: 2995562 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 6605219 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.3073. Min Act: -0.1700
Data Index: 3190020 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.3073. Min Act: -0.1700
Data Index: 92896 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.3698. Min Act: -0.1700
Data Index: 1931157 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 183636 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 2799363 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.1823. Min Act: -0.1700
Data Index: 8309125 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 5939350 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 5133862 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 667963 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6823. Min Range: -8.6823
Max Act: 8.2448. Min Act: -0.1700
Data Index: 5615347 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19