Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2032. Min Range: -6.2032
Max Act: 6.2032. Min Act: -0.1700
Data Index: 8817448 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2032. Min Range: -6.2032
Max Act: 6.1407. Min Act: -0.1700
Data Index: 7841264 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9532. Min Act: -0.1700
Data Index: 3886151 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9532. Min Act: -0.1700
Data Index: 7925578 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9220. Min Act: -0.1700
Data Index: 7347252 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9220. Min Act: -0.1700
Data Index: 892142 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9220. Min Act: -0.1700
Data Index: 3170968 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8907. Min Act: -0.1700
Data Index: 7373305 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8595. Min Act: -0.1700
Data Index: 6211004 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 6194044 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 5083041 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 6829341 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7970. Min Act: -0.1700
Data Index: 2636822 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7970. Min Act: -0.1700
Data Index: 612313 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7970. Min Act: -0.1700
Data Index: 4683208 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7657. Min Act: -0.1700
Data Index: 3283278 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7657. Min Act: -0.1700
Data Index: 5347345 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7970. Min Act: -0.1700
Data Index: 2531415 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7657. Min Act: -0.1700
Data Index: 4674634 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7345. Min Act: -0.1700
Data Index: 8539781 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19