Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5895. Min Range: -11.5895
Max Act: 11.5895. Min Act: -0.1700
Data Index: 3564554 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5895. Min Range: -11.5895
Max Act: 11.2145. Min Act: -0.1700
Data Index: 6505172 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5895. Min Range: -11.5895
Max Act: 11.2145. Min Act: -0.1700
Data Index: 7996999 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5895. Min Range: -11.5895
Max Act: 11.2145. Min Act: -0.1700
Data Index: 3564557 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5895. Min Range: -11.5895
Max Act: 11.1520. Min Act: -0.1700
Data Index: 3146646 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.9645. Min Act: -0.1700
Data Index: 3086524 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.9645. Min Act: -0.1700
Data Index: 3267872 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.9645. Min Act: -0.1700
Data Index: 3564553 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.9020. Min Act: -0.1700
Data Index: 3667580 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7770. Min Act: -0.1700
Data Index: 8101817 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7770. Min Act: -0.1700
Data Index: 5483221 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7770. Min Act: -0.1700
Data Index: 7180840 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7770. Min Act: -0.1700
Data Index: 8025362 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.8395. Min Act: -0.1700
Data Index: 8540496 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7770. Min Act: -0.1700
Data Index: 2441990 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7145. Min Act: -0.1700
Data Index: 1778501 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.7145. Min Act: -0.1700
Data Index: 577702 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.5895. Min Act: -0.1700
Data Index: 6139750 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.5895. Min Act: -0.1700
Data Index: 6855316 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5895. Min Range: -11.5895
Max Act: 10.5895. Min Act: -0.1700
Data Index: 5452912 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19