Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4593 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.2950. Min Act: -0.1700
Data Index: 3763019 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.2325. Min Act: -0.1700
Data Index: 3704293 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.1388. Min Act: -0.1700
Data Index: 2971783 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.1388. Min Act: -0.1700
Data Index: 1922123 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.1075. Min Act: -0.1700
Data Index: 4444347 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.1075. Min Act: -0.1700
Data Index: 3067897 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2950. Min Range: -5.2950
Max Act: 5.1075. Min Act: -0.1700
Data Index: 3042849 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.9513. Min Act: -0.1700
Data Index: 2118239 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.9825. Min Act: -0.1700
Data Index: 3609231 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.9200. Min Act: -0.1700
Data Index: 2023340 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.9200. Min Act: -0.1700
Data Index: 7717515 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8888. Min Act: -0.1700
Data Index: 5820617 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8888. Min Act: -0.1700
Data Index: 6184676 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8575. Min Act: -0.1700
Data Index: 118131 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8575. Min Act: -0.1700
Data Index: 5106205 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8263. Min Act: -0.1700
Data Index: 3609239 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8263. Min Act: -0.1700
Data Index: 8312654 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8263. Min Act: -0.1700
Data Index: 8486954 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.8263. Min Act: -0.1700
Data Index: 3609224 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2950. Min Range: -5.2950
Max Act: 4.7950. Min Act: -0.1700
Data Index: 4650902 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19