Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1036 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.3584. Min Act: -0.1700
Data Index: 4598434 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.3427. Min Act: -0.1700
Data Index: 1416404 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.3113. Min Act: -0.1700
Data Index: 6859425 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.3113. Min Act: -0.1700
Data Index: 4850371 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.3113. Min Act: -0.1700
Data Index: 953592 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.3113. Min Act: -0.1700
Data Index: 452743 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2799. Min Act: -0.1700
Data Index: 163428 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2956. Min Act: -0.1700
Data Index: 4037103 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2642. Min Act: -0.1700
Data Index: 7325189 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2799. Min Act: -0.1700
Data Index: 1589747 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2013. Min Act: -0.1700
Data Index: 863317 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2170. Min Act: -0.1700
Data Index: 740560 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2799. Min Act: -0.1700
Data Index: 1049817 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2013. Min Act: -0.1700
Data Index: 2877668 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2328. Min Act: -0.1700
Data Index: 2566233 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2328. Min Act: -0.1700
Data Index: 255541 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2170. Min Act: -0.1700
Data Index: 7101482 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2013. Min Act: -0.1700
Data Index: 4043570 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.2013. Min Act: -0.1700
Data Index: 7411928 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3584. Min Range: -3.3584
Max Act: 3.1856. Min Act: -0.1700
Data Index: 278226 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19