Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.9317. Min Act: -0.1700
Data Index: 4688497 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.6504. Min Act: -0.1700
Data Index: 593748 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.5879. Min Act: -0.1700
Data Index: 1325779 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.6192. Min Act: -0.1700
Data Index: 8170821 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.5254. Min Act: -0.1700
Data Index: 861248 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4942. Min Act: -0.1700
Data Index: 2014916 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4942. Min Act: -0.1700
Data Index: 8002676 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4942. Min Act: -0.1700
Data Index: 6879018 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4317. Min Act: -0.1700
Data Index: 7836042 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4317. Min Act: -0.1700
Data Index: 712694 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 6119141 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4629. Min Act: -0.1700
Data Index: 7186171 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4317. Min Act: -0.1700
Data Index: 593749 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 5718041 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 1337232 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 2623793 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4317. Min Act: -0.1700
Data Index: 8409777 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 7806237 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 4682110 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9317. Min Range: -4.9317
Max Act: 4.4004. Min Act: -0.1700
Data Index: 3896530 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19