Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.4492. Min Act: -0.1700
Data Index: 8293455 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.3867. Min Act: -0.1700
Data Index: 43420 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.1367. Min Act: -0.1700
Data Index: 8564081 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.1367. Min Act: -0.1700
Data Index: 4549900 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.1367. Min Act: -0.1700
Data Index: 1660855 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.0117. Min Act: -0.1700
Data Index: 7064956 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4492. Min Range: -8.4492
Max Act: 8.0117. Min Act: -0.1700
Data Index: 6446130 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8867. Min Act: -0.1700
Data Index: 7705852 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8867. Min Act: -0.1700
Data Index: 817610 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8867. Min Act: -0.1700
Data Index: 4249448 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8867. Min Act: -0.1700
Data Index: 451522 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8242. Min Act: -0.1700
Data Index: 378513 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8242. Min Act: -0.1700
Data Index: 2532037 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8242. Min Act: -0.1700
Data Index: 7572922 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.7617. Min Act: -0.1700
Data Index: 4646786 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.7617. Min Act: -0.1700
Data Index: 5342273 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.7617. Min Act: -0.1700
Data Index: 583110 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.8242. Min Act: -0.1700
Data Index: 1224768 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.7617. Min Act: -0.1700
Data Index: 8535811 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4492. Min Range: -8.4492
Max Act: 7.7617. Min Act: -0.1700
Data Index: 41816 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19