Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1599 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.7631. Min Act: -0.1700
Data Index: 6013720 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.7006. Min Act: -0.1700
Data Index: 444213 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.7006. Min Act: -0.1700
Data Index: 2336218 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.6381. Min Act: -0.1700
Data Index: 3792936 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.5756. Min Act: -0.1700
Data Index: 444210 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.5444. Min Act: -0.1700
Data Index: 3051803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.5131. Min Act: -0.1700
Data Index: 2625744 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.5131. Min Act: -0.1700
Data Index: 7942539 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.5131. Min Act: -0.1700
Data Index: 1088646 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4819. Min Act: -0.1700
Data Index: 4760967 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4819. Min Act: -0.1700
Data Index: 7011526 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4819. Min Act: -0.1700
Data Index: 121390 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4819. Min Act: -0.1700
Data Index: 2336219 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4194. Min Act: -0.1700
Data Index: 6937641 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4194. Min Act: -0.1700
Data Index: 801450 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4194. Min Act: -0.1700
Data Index: 6240426 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.4506. Min Act: -0.1700
Data Index: 7942538 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.3881. Min Act: -0.1700
Data Index: 4006609 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.3881. Min Act: -0.1700
Data Index: 4006685 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7631. Min Range: -5.7631
Max Act: 5.3569. Min Act: -0.1700
Data Index: 6869784 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19