Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5867 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.7718. Min Act: -0.1700
Data Index: 2238984 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.5843. Min Act: -0.1700
Data Index: 5376863 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.5843. Min Act: -0.1700
Data Index: 8240000 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.3968. Min Act: -0.1700
Data Index: 8070211 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.4593. Min Act: -0.1700
Data Index: 4386450 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.3968. Min Act: -0.1700
Data Index: 7306696 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.3343. Min Act: -0.1700
Data Index: 2238988 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.3343. Min Act: -0.1700
Data Index: 8109064 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.2093. Min Act: -0.1700
Data Index: 2238987 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.2093. Min Act: -0.1700
Data Index: 2822059 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.2093. Min Act: -0.1700
Data Index: 7094755 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.2093. Min Act: -0.1700
Data Index: 6156303 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.1468. Min Act: -0.1700
Data Index: 7704051 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.0843. Min Act: -0.1700
Data Index: 32498 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7718. Min Range: -10.7718
Max Act: 9.9593. Min Act: -0.1700
Data Index: 6014969 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.0218. Min Act: -0.1700
Data Index: 8289897 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.0218. Min Act: -0.1700
Data Index: 2117813 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.0218. Min Act: -0.1700
Data Index: 1937855 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7718. Min Range: -10.7718
Max Act: 10.0218. Min Act: -0.1700
Data Index: 6389533 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7718. Min Range: -10.7718
Max Act: 9.9593. Min Act: -0.1700
Data Index: 3617079 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19