Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.9645. Min Act: -0.1700
Data Index: 1048676 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.8395. Min Act: -0.1700
Data Index: 8078761 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.7145. Min Act: -0.1700
Data Index: 4539755 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.5895. Min Act: -0.1700
Data Index: 6017733 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.4645. Min Act: -0.1700
Data Index: 4489362 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.4020. Min Act: -0.1700
Data Index: 4709473 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.3395. Min Act: -0.1700
Data Index: 2099570 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.4020. Min Act: -0.1700
Data Index: 7247904 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.2770. Min Act: -0.1700
Data Index: 7683884 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.2770. Min Act: -0.1700
Data Index: 5578149 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.2145. Min Act: -0.1700
Data Index: 5992173 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.2145. Min Act: -0.1700
Data Index: 8106146 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.2145. Min Act: -0.1700
Data Index: 2375099 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.0895. Min Act: -0.1700
Data Index: 2842012 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.1520. Min Act: -0.1700
Data Index: 5198745 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.1520. Min Act: -0.1700
Data Index: 3473728 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.0895. Min Act: -0.1700
Data Index: 1265611 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.0270. Min Act: -0.1700
Data Index: 3915546 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.0270. Min Act: -0.1700
Data Index: 3989363 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9645. Min Range: -10.9645
Max Act: 10.0270. Min Act: -0.1700
Data Index: 7102631 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19