Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.8571. Min Act: -0.1700
Data Index: 6070754 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.8259. Min Act: -0.1700
Data Index: 2918786 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.8884. Min Act: -0.1700
Data Index: 1637606 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.8571. Min Act: -0.1700
Data Index: 1780915 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.8571. Min Act: -0.1700
Data Index: 723892 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.7946. Min Act: -0.1700
Data Index: 8405882 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.7946. Min Act: -0.1700
Data Index: 878959 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.7634. Min Act: -0.1700
Data Index: 7179249 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.7946. Min Act: -0.1700
Data Index: 6846170 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.7321. Min Act: -0.1700
Data Index: 7603987 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6696. Min Act: -0.1700
Data Index: 7276755 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6696. Min Act: -0.1700
Data Index: 1683875 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6384. Min Act: -0.1700
Data Index: 8661495 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6071. Min Act: -0.1700
Data Index: 5151732 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6384. Min Act: -0.1700
Data Index: 297649 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6071. Min Act: -0.1700
Data Index: 8362974 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.6071. Min Act: -0.1700
Data Index: 3711804 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.5759. Min Act: -0.1700
Data Index: 5090154 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.5759. Min Act: -0.1700
Data Index: 5275652 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8884. Min Range: -6.8884
Max Act: 6.5446. Min Act: -0.1700
Data Index: 1238877 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19