Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.9700. Min Act: -0.1700
Data Index: 5016541 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.8450. Min Act: -0.1700
Data Index: 6289088 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.8450. Min Act: -0.1700
Data Index: 6970329 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.7825. Min Act: -0.1700
Data Index: 2099578 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.6887. Min Act: -0.1700
Data Index: 821708 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.7200. Min Act: -0.1700
Data Index: 1019469 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.7200. Min Act: -0.1700
Data Index: 260645 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.7200. Min Act: -0.1700
Data Index: 1944372 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.6887. Min Act: -0.1700
Data Index: 5624709 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.6575. Min Act: -0.1700
Data Index: 1946212 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.5950. Min Act: -0.1700
Data Index: 5114915 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.6262. Min Act: -0.1700
Data Index: 5757623 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.5325. Min Act: -0.1700
Data Index: 2524382 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.5325. Min Act: -0.1700
Data Index: 1852368 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.5325. Min Act: -0.1700
Data Index: 3642585 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.5012. Min Act: -0.1700
Data Index: 3533898 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.4700. Min Act: -0.1700
Data Index: 5270869 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.4387. Min Act: -0.1700
Data Index: 1061603 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.4387. Min Act: -0.1700
Data Index: 5285841 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9700. Min Range: -6.9700
Max Act: 6.4075. Min Act: -0.1700
Data Index: 3424997 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19