Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5464. Min Range: -4.5464
Max Act: 4.5464. Min Act: -0.1700
Data Index: 8123465 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5464. Min Range: -4.5464
Max Act: 4.1714. Min Act: -0.1700
Data Index: 4863624 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5464. Min Range: -4.5464
Max Act: 4.0463. Min Act: -0.1700
Data Index: 1232470 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5464. Min Range: -4.5464
Max Act: 4.0151. Min Act: -0.1700
Data Index: 2560510 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9838. Min Act: -0.1700
Data Index: 217442 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9526. Min Act: -0.1700
Data Index: 584133 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9838. Min Act: -0.1700
Data Index: 7527936 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9526. Min Act: -0.1700
Data Index: 495164 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9526. Min Act: -0.1700
Data Index: 628005 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9526. Min Act: -0.1700
Data Index: 2930768 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9526. Min Act: -0.1700
Data Index: 7049572 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9213. Min Act: -0.1700
Data Index: 7186830 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.9213. Min Act: -0.1700
Data Index: 2561522 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8900. Min Act: -0.1700
Data Index: 6146133 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8900. Min Act: -0.1700
Data Index: 591103 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8588. Min Act: -0.1700
Data Index: 3298547 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8588. Min Act: -0.1700
Data Index: 3710262 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8588. Min Act: -0.1700
Data Index: 2173710 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8588. Min Act: -0.1700
Data Index: 5351024 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5464. Min Range: -4.5464
Max Act: 3.8588. Min Act: -0.1700
Data Index: 1228504 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19