Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3740 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1705. Min Range: -5.1705
Max Act: 5.1705. Min Act: -0.1700
Data Index: 2718849 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.7017. Min Act: -0.1700
Data Index: 1120037 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.7017. Min Act: -0.1700
Data Index: 8457403 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.6392. Min Act: -0.1700
Data Index: 8254450 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.6080. Min Act: -0.1700
Data Index: 7938697 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4830. Min Act: -0.1700
Data Index: 7796377 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4830. Min Act: -0.1700
Data Index: 4324041 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 2053581 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 4351611 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4205. Min Act: -0.1700
Data Index: 269184 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4517. Min Act: -0.1700
Data Index: 2375448 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.4205. Min Act: -0.1700
Data Index: 6356693 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 6770039 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 4786844 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 3463088 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 3359000 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 436815 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3892. Min Act: -0.1700
Data Index: 3004211 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3267. Min Act: -0.1700
Data Index: 7162153 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1705. Min Range: -5.1705
Max Act: 4.3580. Min Act: -0.1700
Data Index: 4514003 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19