Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1987 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.8996. Min Act: -0.1700
Data Index: 8427756 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.8683. Min Act: -0.1700
Data Index: 3214357 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.8683. Min Act: -0.1700
Data Index: 8126248 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.6496. Min Act: -0.1700
Data Index: 984339 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.6496. Min Act: -0.1700
Data Index: 4108668 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.6183. Min Act: -0.1700
Data Index: 108497 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.5558. Min Act: -0.1700
Data Index: 1977699 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.5558. Min Act: -0.1700
Data Index: 7209896 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.5558. Min Act: -0.1700
Data Index: 8156608 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.5246. Min Act: -0.1700
Data Index: 4161474 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.5246. Min Act: -0.1700
Data Index: 4967387 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4933. Min Act: -0.1700
Data Index: 5754861 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4621. Min Act: -0.1700
Data Index: 271002 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4933. Min Act: -0.1700
Data Index: 8580812 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4621. Min Act: -0.1700
Data Index: 3335947 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4308. Min Act: -0.1700
Data Index: 4822377 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4933. Min Act: -0.1700
Data Index: 943172 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4308. Min Act: -0.1700
Data Index: 4374809 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4308. Min Act: -0.1700
Data Index: 8423651 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8996. Min Range: -6.8996
Max Act: 6.4308. Min Act: -0.1700
Data Index: 5009108 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19