Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.9100. Min Act: -0.1700
Data Index: 3709666 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.7225. Min Act: -0.1700
Data Index: 4379007 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.5037. Min Act: -0.1700
Data Index: 244383 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.5350. Min Act: -0.1700
Data Index: 3679954 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.4725. Min Act: -0.1700
Data Index: 7224753 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.4412. Min Act: -0.1700
Data Index: 5222446 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.4100. Min Act: -0.1700
Data Index: 652367 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.4100. Min Act: -0.1700
Data Index: 3890778 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.3787. Min Act: -0.1700
Data Index: 4521418 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1604619 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.3162. Min Act: -0.1700
Data Index: 7731353 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.3162. Min Act: -0.1700
Data Index: 1337460 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.3162. Min Act: -0.1700
Data Index: 5045011 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2850. Min Act: -0.1700
Data Index: 6910630 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2850. Min Act: -0.1700
Data Index: 5255490 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2225. Min Act: -0.1700
Data Index: 5064303 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2537. Min Act: -0.1700
Data Index: 986592 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2225. Min Act: -0.1700
Data Index: 952678 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2225. Min Act: -0.1700
Data Index: 6430095 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9100. Min Range: -6.9100
Max Act: 6.2225. Min Act: -0.1700
Data Index: 2807944 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19