Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.6689. Min Act: -0.1700
Data Index: 7016948 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.6376. Min Act: -0.1700
Data Index: 7579208 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.5751. Min Act: -0.1700
Data Index: 7121240 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.5751. Min Act: -0.1700
Data Index: 8323532 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.5439. Min Act: -0.1700
Data Index: 1124869 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.5126. Min Act: -0.1700
Data Index: 5452765 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.5126. Min Act: -0.1700
Data Index: 4818688 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.5126. Min Act: -0.1700
Data Index: 4457301 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4814. Min Act: -0.1700
Data Index: 391601 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4814. Min Act: -0.1700
Data Index: 8602446 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4189. Min Act: -0.1700
Data Index: 7596774 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4501. Min Act: -0.1700
Data Index: 6453528 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4501. Min Act: -0.1700
Data Index: 6184360 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4501. Min Act: -0.1700
Data Index: 3584480 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4189. Min Act: -0.1700
Data Index: 3787732 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4189. Min Act: -0.1700
Data Index: 3145586 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4501. Min Act: -0.1700
Data Index: 5009327 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4189. Min Act: -0.1700
Data Index: 882110 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.4189. Min Act: -0.1700
Data Index: 2975976 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6689. Min Range: -4.6689
Max Act: 4.3876. Min Act: -0.1700
Data Index: 6143034 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19