Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.8887. Min Act: -0.1700
Data Index: 1566443 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3887. Min Act: -0.1700
Data Index: 1775105 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3887. Min Act: -0.1700
Data Index: 117796 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.3575. Min Act: -0.1700
Data Index: 7907708 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2950. Min Act: -0.1700
Data Index: 1755049 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2325. Min Act: -0.1700
Data Index: 5920684 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2325. Min Act: -0.1700
Data Index: 1771050 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2012. Min Act: -0.1700
Data Index: 7349113 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2012. Min Act: -0.1700
Data Index: 2239495 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2012. Min Act: -0.1700
Data Index: 5078950 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2012. Min Act: -0.1700
Data Index: 4315345 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.2012. Min Act: -0.1700
Data Index: 8611437 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.1387. Min Act: -0.1700
Data Index: 7633899 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.1387. Min Act: -0.1700
Data Index: 4170187 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.1387. Min Act: -0.1700
Data Index: 330214 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.1075. Min Act: -0.1700
Data Index: 5277837 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.1075. Min Act: -0.1700
Data Index: 6541003 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.0762. Min Act: -0.1700
Data Index: 4539841 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.0762. Min Act: -0.1700
Data Index: 8681100 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8887. Min Range: -7.8887
Max Act: 7.0450. Min Act: -0.1700
Data Index: 2466781 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19