Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0012. Min Range: -8.0012
Max Act: 8.0012. Min Act: -0.1700
Data Index: 7313798 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.8762. Min Act: -0.1700
Data Index: 2307238 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.5950. Min Act: -0.1700
Data Index: 4289007 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.5950. Min Act: -0.1700
Data Index: 7297602 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.5950. Min Act: -0.1700
Data Index: 537142 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.4387. Min Act: -0.1700
Data Index: 3601517 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.4387. Min Act: -0.1700
Data Index: 5469017 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.4387. Min Act: -0.1700
Data Index: 1588937 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.4075. Min Act: -0.1700
Data Index: 6569494 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.3450. Min Act: -0.1700
Data Index: 4414195 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.3762. Min Act: -0.1700
Data Index: 4734734 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.3762. Min Act: -0.1700
Data Index: 2143877 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.3450. Min Act: -0.1700
Data Index: 2582465 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.3450. Min Act: -0.1700
Data Index: 6275843 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.3450. Min Act: -0.1700
Data Index: 5740741 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.2825. Min Act: -0.1700
Data Index: 656777 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.2512. Min Act: -0.1700
Data Index: 811071 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.2825. Min Act: -0.1700
Data Index: 8055797 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.2512. Min Act: -0.1700
Data Index: 1699458 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0012. Min Range: -8.0012
Max Act: 7.2200. Min Act: -0.1700
Data Index: 2770691 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19