Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0867. Min Range: -5.0867
Max Act: 5.0867. Min Act: -0.1700
Data Index: 1555748 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0867. Min Range: -5.0867
Max Act: 5.0242. Min Act: -0.1700
Data Index: 8806975 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.9617. Min Act: -0.1700
Data Index: 7912015 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.9617. Min Act: -0.1700
Data Index: 3849546 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.9305. Min Act: -0.1700
Data Index: 4495141 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8992. Min Act: -0.1700
Data Index: 2724712 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8680. Min Act: -0.1700
Data Index: 1359312 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8680. Min Act: -0.1700
Data Index: 4379735 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8680. Min Act: -0.1700
Data Index: 4504845 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8367. Min Act: -0.1700
Data Index: 2120720 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8680. Min Act: -0.1700
Data Index: 5221886 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8680. Min Act: -0.1700
Data Index: 2754277 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8367. Min Act: -0.1700
Data Index: 5239285 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8367. Min Act: -0.1700
Data Index: 393411 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.7742. Min Act: -0.1700
Data Index: 8432888 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5700317 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.7742. Min Act: -0.1700
Data Index: 2315949 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.7742. Min Act: -0.1700
Data Index: 7292419 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.7742. Min Act: -0.1700
Data Index: 2578263 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0867. Min Range: -5.0867
Max Act: 4.7430. Min Act: -0.1700
Data Index: 6376974 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19