Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5174 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0094. Min Range: -8.0094
Max Act: 8.0094. Min Act: -0.1700
Data Index: 8403518 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0094. Min Range: -8.0094
Max Act: 8.0094. Min Act: -0.1700
Data Index: 3491373 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.8219. Min Act: -0.1700
Data Index: 7234966 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.6032. Min Act: -0.1700
Data Index: 5905260 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.5407. Min Act: -0.1700
Data Index: 592105 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.4469. Min Act: -0.1700
Data Index: 3228436 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.4469. Min Act: -0.1700
Data Index: 4686894 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.4469. Min Act: -0.1700
Data Index: 1401768 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.3844. Min Act: -0.1700
Data Index: 7306569 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.3532. Min Act: -0.1700
Data Index: 5319806 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.3844. Min Act: -0.1700
Data Index: 3267699 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.3532. Min Act: -0.1700
Data Index: 2709316 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.3844. Min Act: -0.1700
Data Index: 489055 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.3532. Min Act: -0.1700
Data Index: 6526593 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.2907. Min Act: -0.1700
Data Index: 4611938 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.2907. Min Act: -0.1700
Data Index: 902699 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.2907. Min Act: -0.1700
Data Index: 7433233 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.2907. Min Act: -0.1700
Data Index: 133830 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.2907. Min Act: -0.1700
Data Index: 8131781 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0094. Min Range: -8.0094
Max Act: 7.2594. Min Act: -0.1700
Data Index: 5797320 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19