Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2650. Min Range: -5.2650
Max Act: 5.2650. Min Act: -0.1700
Data Index: 7427083 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2650. Min Range: -5.2650
Max Act: 5.1088. Min Act: -0.1700
Data Index: 981569 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2650. Min Range: -5.2650
Max Act: 5.0150. Min Act: -0.1700
Data Index: 4385158 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.9838. Min Act: -0.1700
Data Index: 2450023 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.9838. Min Act: -0.1700
Data Index: 5358730 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.9525. Min Act: -0.1700
Data Index: 6965725 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8900. Min Act: -0.1700
Data Index: 7464574 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8900. Min Act: -0.1700
Data Index: 306218 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8900. Min Act: -0.1700
Data Index: 5674872 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8900. Min Act: -0.1700
Data Index: 8418658 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8900. Min Act: -0.1700
Data Index: 8301387 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8275. Min Act: -0.1700
Data Index: 6280612 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8275. Min Act: -0.1700
Data Index: 3368332 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.8588. Min Act: -0.1700
Data Index: 5360347 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.7650. Min Act: -0.1700
Data Index: 3575226 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.7963. Min Act: -0.1700
Data Index: 4507606 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.7963. Min Act: -0.1700
Data Index: 2125122 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.7963. Min Act: -0.1700
Data Index: 3963727 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.7963. Min Act: -0.1700
Data Index: 2395579 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2650. Min Range: -5.2650
Max Act: 4.7650. Min Act: -0.1700
Data Index: 4362482 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19